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

    Neuronpedia

    INDEX
    Explanations

    single

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Raiders
    -0.06
    .GetKey
    -0.06
     Costa
    -0.06
     Kaynak
    -0.06
    _rsa
    -0.06
    .configuration
    -0.06
    .Middle
    -0.06
     μέρος
    -0.06
    osi
    -0.06
    [row
    -0.05
    POSITIVE LOGITS
    erving
    0.07
    0.07
    ành
    0.07
    .netty
    0.06
    0.06
    §ط
    0.06
    ming
    0.06
    -serving
    0.06
     shorthand
    0.06
    -commit
    0.06
    Act Density 0.004%

    No Known Activations