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

    Neuronpedia

    INDEX
    Explanations

    studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Initially
    -0.06
     dando
    -0.06
    _o
    -0.06
     vulnerable
    -0.06
     sands
    -0.06
     oversight
    -0.06
    Naming
    -0.06
     nobody
    -0.06
    歩
    -0.05
    іка
    -0.05
    POSITIVE LOGITS
     yapı
    0.07
    ("../
    0.06
    ombat
    0.06
     základní
    0.06
    QObject
    0.06
    asts
    0.06
    obbies
    0.06
     originating
    0.06
    adí
    0.06
    *↵
    0.06
    Act Density 0.078%

    No Known Activations