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

    Neuronpedia

    INDEX
    Explanations

    Berkeley

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    758
    -0.07
     Alive
    -0.07
    .prop
    -0.06
    ")==
    -0.06
     Twe
    -0.06
     resourceId
    -0.06
     opsiyon
    -0.06
    Ctl
    -0.06
    tbody
    -0.06
    ..."
    -0.06
    POSITIVE LOGITS
     Berkeley
    0.15
    keley
    0.09
     arbitrary
    0.06
     Vertex
    0.06
    itesi
    0.06
    OH
    0.06
     Families
    0.06
    /loose
    0.06
     벽
    0.06
    いつ
    0.06
    Act Density 0.001%

    No Known Activations