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

    Neuronpedia

    INDEX
    Explanations

    code files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Manifest
    -0.07
     tint
    -0.07
     Girl
    -0.07
     Zig
    -0.06
    ruption
    -0.06
     Blink
    -0.06
     Surg
    -0.06
     lingering
    -0.06
    这几年
    -0.06
    因地
    -0.06
    POSITIVE LOGITS
    jual
    0.09
     sculptures
    0.07
     Palace
    0.07
     إعادة
    0.07
    意識
    0.07
     Quản
    0.07
     activation
    0.07
    거래
    0.07
    待
    0.06
    _bound
    0.06
    Act Density 0.004%

    No Known Activations