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

    Neuronpedia

    INDEX
    Explanations

    probability calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .android
    -0.06
     Beckham
    -0.06
    nite
    -0.06
    .layer
    -0.06
    PACE
    -0.06
     sebuah
    -0.06
     Less
    -0.06
    웨
    -0.06
    probably
    -0.06
     witches
    -0.06
    POSITIVE LOGITS
    ��
    0.06
    _Cancel
    0.06
    Documento
    0.06
     toxic
    0.06
    映画
    0.06
    LOAD
    0.06
    ショ
    0.06
     aload
    0.06
    �
    0.06
    load
    0.06
    Act Density 0.001%

    No Known Activations