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

    Neuronpedia

    INDEX
    Explanations

    requesting more information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lices
    -0.07
     reinstall
    -0.06
     מח
    -0.06
    啵
    -0.06
    .lbl
    -0.06
     ldc
    -0.06
    怎
    -0.06
     цел
    -0.06
     repet
    -0.06
    ﻧ
    -0.06
    POSITIVE LOGITS
    .Executor
    0.07
    阿里
    0.07
    キング
    0.07
    .Down
    0.07
    呼和浩特
    0.07
    rokes
    0.07
    广告
    0.07
     asylum
    0.07
    evaluate
    0.07
     externally
    0.07
    Act Density 0.018%

    No Known Activations