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

    Neuronpedia

    INDEX
    Explanations

    say "."

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _setup
    -0.07
     Ruiz
    -0.07
     widget
    -0.07
    Curso
    -0.07
     noticias
    -0.07
    Fun
    -0.07
    |.↵
    -0.06
     Boxes
    -0.06
     Mine
    -0.06
    iler
    -0.06
    POSITIVE LOGITS
     bruk
    0.07
    activ
    0.07
    anium
    0.06
     Мик
    0.06
    اگ
    0.06
    RequestParam
    0.06
    189
    0.06
    _kategori
    0.06
     ^{°}
    0.06
    erchant
    0.06
    Act Density 0.026%

    No Known Activations