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

    Neuronpedia

    INDEX
    Explanations

    authorization, validation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UserService
    -0.07
    金
    -0.07
     bytearray
    -0.07
    ernal
    -0.07
    �
    -0.06
    _versions
    -0.06
     wealthy
    -0.06
     Colo
    -0.06
     cess
    -0.06
    jerne
    -0.06
    POSITIVE LOGITS
    auté
    0.07
    .Unity
    0.06
     Trou
    0.06
    _Msk
    0.06
     Irving
    0.06
     Unable
    0.06
     cí
    0.06
     acknowledged
    0.06
     wholesale
    0.06
    SER
    0.06
    Act Density 0.020%

    No Known Activations