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

    Neuronpedia

    INDEX
    Explanations

    Common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _reward
    -0.07
     ensemble
    -0.07
     Kemp
    -0.06
    陈
    -0.06
     мор
    -0.06
    .Re
    -0.06
    -Re
    -0.06
     instead
    -0.06
    chemical
    -0.06
    とう
    -0.06
    POSITIVE LOGITS
    office
    0.07
     дів
    0.07
     розповід
    0.06
    FC
    0.06
    ंघ
    0.06
    ishlist
    0.06
    ской
    0.06
    ".$_
    0.06
    String
    0.06
    (schema
    0.06
    Act Density 0.035%

    No Known Activations