Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    statements of fact or assertions related to processes or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "It is" or "It's" at the beginning of a sentence

    np_acts-logits-general · gemini-2.0-flash

    states of possibility and difficulty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    География
    -0.72
     Agamemnon
    -0.70
    хьтан
    -0.67
    Personendaten
    -0.64
     Molière
    -0.63
     AssemblyProduct
    -0.62
    Biografía
    -0.61
    复制代码
    -0.58
    themselves
    -0.58
    tvguidetime
    -0.57
    POSITIVE LOGITS
     possible
    1.16
    possible
    1.01
     raining
    1.01
     impossible
    0.94
     snowing
    0.94
     mogelijk
    0.85
     POSSIBLE
    0.85
    Possible
    0.84
     unclear
    0.83
     difficult
    0.83
    Act Density 0.425%

    No Known Activations