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

    Neuronpedia

    INDEX
    Explanations

    human

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ad
    -0.08
    _BAR
    -0.07
    SnackBar
    -0.07
    -width
    -0.07
    دار
    -0.07
     心
    -0.07
     Amp
    -0.06
     pul
    -0.06
    uls
    -0.06
    getDb
    -0.06
    POSITIVE LOGITS
     Human
    0.10
    Human
    0.09
     human
    0.07
    _opts
    0.06
    las
    0.06
    _DEFINITION
    0.06
    わせ
    0.06
     shuts
    0.06
     consumer
    0.06
    esign
    0.05
    Act Density 0.011%

    No Known Activations