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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ᡵ
    -0.07
    适当
    -0.07
    ি�
    -0.07
    знак
    -0.07
    LOOK
    -0.07
    西瓜
    -0.07
     filepath
    -0.06
     nephew
    -0.06
     zost
    -0.06
    裡面
    -0.06
    POSITIVE LOGITS
    arty
    0.08
    镑
    0.07
     robbed
    0.07
    .Cast
    0.07
    更为
    0.07
    ]-
    0.07
    .Collection
    0.07
    .Format
    0.07
    svp
    0.07
    @RunWith
    0.06
    Act Density 0.032%

    No Known Activations