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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     นาย
    -0.07
     jealous
    -0.06
    _budget
    -0.06
    -way
    -0.06
    initial
    -0.06
     placement
    -0.06
    .readValue
    -0.06
    _commit
    -0.06
    >({↵
    -0.06
     makin
    -0.06
    POSITIVE LOGITS
    عي
    0.07
     círk
    0.06
    енти
    0.06
    mět
    0.06
     ASUS
    0.06
    ımı
    0.06
    يك
    0.06
     remark
    0.06
     nær
    0.06
    .onStart
    0.06
    Act Density 0.065%

    No Known Activations