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

    Neuronpedia

    INDEX
    Explanations

    .com

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    grams
    -0.07
     Gi
    -0.06
    י�
    -0.06
    lr
    -0.06
     jul
    -0.06
    larını
    -0.06
    ющие
    -0.06
    ToObject
    -0.06
     sentencing
    -0.06
    enght
    -0.06
    POSITIVE LOGITS
     вив
    0.07
    加载
    0.06
    apeake
    0.06
     adultery
    0.06
     appreh
    0.06
    _STATUS
    0.06
     NM
    0.06
    (display
    0.06
    (Customer
    0.06
    （笑
    0.06
    Act Density 0.016%

    No Known Activations