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

    Neuronpedia

    INDEX
    Explanations

    them

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    테
    -0.07
     книги
    -0.06
    (Service
    -0.06
    اوی
    -0.06
    portunity
    -0.06
    ฤษ
    -0.06
    公園
    -0.06
     parks
    -0.06
    Serial
    -0.06
    itory
    -0.06
    POSITIVE LOGITS
    [tag
    0.06
     toString
    0.06
     Ah
    0.06
    やる夫
    0.06
     marque
    0.06
     意
    0.06
    .now
    0.06
     Usuarios
    0.06
     pundits
    0.06
    .linspace
    0.06
    Act Density 0.000%

    No Known Activations