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

    Neuronpedia

    INDEX
    Explanations

    say capital word

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Chung
    -0.07
    ﮑ
    -0.07
    高尚
    -0.07
    走出
    -0.07
    nas
    -0.07
    (reference
    -0.07
     Phạm
    -0.07
    ActivityCreated
    -0.07
    agner
    -0.07
    argas
    -0.07
    POSITIVE LOGITS
    dialog
    0.07
     prompt
    0.07
    .MinValue
    0.07
     Vanity
    0.07
    acious
    0.07
    .task
    0.07
    bk
    0.06
    ous
    0.06
     Client
    0.06
    上限
    0.06
    Act Density 0.003%

    No Known Activations