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

    Neuronpedia

    INDEX
    Explanations

    concepts related to research methodologies and the ethical implications of consent

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

    Statements of inadequacy or insufficiency

    np_acts-logits-general · gemini-2.0-flash

    insufficient or flawed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BagConstraints
    -0.55
    没事
    -0.55
    انيف
    -0.53
     Happen
    -0.53
    strix
    -0.52
     Wiktionnaire
    -0.51
    ModelMap
    -0.51
    ousand
    -0.50
    pecha
    -0.50
     محفوظة
    -0.49
    POSITIVE LOGITS
     lacks
    1.35
     fails
    1.31
     inadequ
    1.21
     insufficient
    1.18
     lacked
    1.18
     inadequate
    1.16
     fail
    1.10
     lack
    1.09
     poorly
    1.03
     misses
    1.03
    Act Density 0.969%

    No Known Activations