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

    Neuronpedia

    INDEX
    Explanations

    gentle handling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dao
    -0.08
     vidět
    -0.07
     ヴ
    -0.07
    تبال
    -0.06
     passage
    -0.06
    êt
    -0.06
    λε
    -0.06
     ata
    -0.06
     uur
    -0.06
    卡
    -0.06
    POSITIVE LOGITS
    0.08
     знач
    0.07
     cherish
    0.06
    _PAGES
    0.06
     Vacc
    0.06
     опас
    0.06
    scient
    0.06
    _virtual
    0.06
     (!_
    0.06
    .Args
    0.06
    Act Density 0.148%

    No Known Activations