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

    Neuronpedia

    INDEX
    Explanations

    awards and statistics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sce
    -0.07
     BBC
    -0.06
    between
    -0.06
    不知
    -0.06
     credible
    -0.06
    完全
    -0.06
     فريق
    -0.06
     positives
    -0.06
    ingers
    -0.06
    .CL
    -0.06
    POSITIVE LOGITS
    (after
    0.07
     ENT
    0.06
    acad
    0.06
    _ENC
    0.06
     εί
    0.06
    ุปกรณ
    0.06
    .Ver
    0.06
    Alt
    0.06
     Sem
    0.06
    CLAIM
    0.06
    Act Density 0.066%

    No Known Activations