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

    Neuronpedia

    INDEX
    Explanations

    About children

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -centered
    -0.07
     Nhĩ
    -0.07
    타
    -0.07
     선
    -0.06
     Corm
    -0.06
    タ
    -0.06
    式
    -0.06
    �
    -0.06
    쳤다
    -0.06
    檢
    -0.06
    POSITIVE LOGITS
    IGIN
    0.07
     slavery
    0.07
     ngồi
    0.07
    _bg
    0.07
    (grad
    0.07
    ombine
    0.06
    (jLabel
    0.06
    (cube
    0.06
    alphabet
    0.06
    -reply
    0.06
    Act Density 0.000%

    No Known Activations