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

    Neuronpedia

    INDEX
    Explanations

    Biographies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ({'
    -0.07
    先生
    -0.07
     Debt
    -0.07
     Roles
    -0.06
    кої
    -0.06
    ()↵↵
    -0.06
    واع
    -0.06
     Five
    -0.06
    _connection
    -0.06
    кого
    -0.06
    POSITIVE LOGITS
     toItem
    0.07
     ฟ
    0.06
    .PNG
    0.06
     bolest
    0.06
     тов
    0.06
     knob
    0.06
    <Block
    0.06
    CLIENT
    0.06
     dày
    0.06
    (phase
    0.06
    Act Density 0.057%

    No Known Activations