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

    Neuronpedia

    INDEX
    Explanations

    Exchange/Conversation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ського
    -0.07
    strategy
    -0.06
    Reward
    -0.06
     акти
    -0.06
     وزارت
    -0.06
    代
    -0.06
    ється
    -0.06
    퓨
    -0.06
    bare
    -0.06
    odynam
    -0.06
    POSITIVE LOGITS
    ,True
    0.07
     CEL
    0.06
    _gs
    0.06
     ε�
    0.06
     sokak
    0.06
     tslint
    0.06
    REFER
    0.06
     Mansion
    0.06
    考虑
    0.06
    (conv
    0.06
    Act Density 0.026%

    No Known Activations