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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and their implications

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

    allowed to be left untreated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wikia
    -0.38
    lapsingToolbar
    -0.37
     Wiel
    -0.34
     Zwar
    -0.34
    ribadian
    -0.33
     Zelt
    -0.33
    IMENTAL
    -0.33
     Akti
    -0.32
     Felsen
    -0.31
     Fy
    -0.31
    POSITIVE LOGITS
     allowed
    1.45
     Allowed
    1.29
    allowed
    1.17
    Allowed
    1.09
     permitted
    1.08
     ALLOWED
    1.08
     permitido
    0.98
    ALLOWED
    0.92
    permitted
    0.82
     encouraged
    0.80
    Act Density 0.130%

    No Known Activations