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

    Neuronpedia

    INDEX
    Explanations

    say "2"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    榫
    -0.07
    _subtitle
    -0.07
     sommes
    -0.07
    嗄
    -0.07
     للم
    -0.07
    ˎ
    -0.07
    доров
    -0.07
     canv
    -0.07
    诱人
    -0.07
    _notifier
    -0.07
    POSITIVE LOGITS
    hil
    0.07
    丽
    0.07
    Ser
    0.07
     methodName
    0.07
     rogue
    0.07
     Richard
    0.07
     Mant
    0.07
     WA
    0.07
    ga
    0.06
     Aristotle
    0.06
    Act Density 0.000%

    No Known Activations