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

    Neuronpedia

    INDEX
    Explanations

    webhooks and APIs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Flo
    -0.07
     或
    -0.07
    кра
    -0.06
    forall
    -0.06
    resource
    -0.06
    included
    -0.06
     فرو
    -0.06
     Estado
    -0.06
    Chef
    -0.06
    enum
    -0.06
    POSITIVE LOGITS
    .CommandType
    0.07
     namedtuple
    0.07
     Seznam
    0.07
    ]?.
    0.06
    .Observable
    0.06
     δύ
    0.06
     incarn
    0.06
     tie
    0.06
    ...(
    0.06
     Kinh
    0.06
    Act Density 0.022%

    No Known Activations