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

    Neuronpedia

    INDEX
    Explanations

    state

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Psr
    -0.08
    .GREEN
    -0.08
     harassed
    -0.08
    InlineData
    -0.07
     stimulation
    -0.07
     candidacy
    -0.07
    (Direction
    -0.07
    _VALUES
    -0.07
    .Authentication
    -0.07
    _eval
    -0.07
    POSITIVE LOGITS
     页面
    0.08
    million
    0.07
    ⎜
    0.07
    最大的
    0.07
     engine
    0.07
    ,ch
    0.07
    percent
    0.06
    ⾨
    0.06
    ﺡ
    0.06
    mployee
    0.06
    Act Density 0.822%

    No Known Activations