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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    indy
    -0.06
     vict
    -0.06
    _intensity
    -0.06
    Kate
    -0.06
    、本
    -0.06
    /min
    -0.06
     mentre
    -0.06
     agony
    -0.06
    (domain
    -0.06
    <My
    -0.06
    POSITIVE LOGITS
     cousin
    0.06
     삶
    0.06
     Scrolls
    0.06
     insp
    0.06
     baptism
    0.06
     husband
    0.06
    #
    0.06
     purpose
    0.06
    <Void
    0.06
    idar
    0.05
    Act Density 0.030%

    No Known Activations