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

    Neuronpedia

    INDEX
    Explanations

    Avoiding duplicates

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fears
    -0.07
    -case
    -0.07
     erected
    -0.06
     Superman
    -0.06
    _sensitive
    -0.06
    descriptor
    -0.06
     case
    -0.06
     sandwich
    -0.06
    list
    -0.06
    Chance
    -0.06
    POSITIVE LOGITS
     Malta
    0.07
    เ�
    0.07
    haled
    0.06
     ГО
    0.06
    arn
    0.06
     Дж
    0.06
    AJ
    0.06
     september
    0.06
    (Action
    0.06
     �
    0.06
    Act Density 0.188%

    No Known Activations