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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intellectually
    -0.06
    tí
    -0.06
     đáp
    -0.06
     Law
    -0.06
    .tw
    -0.06
     dět
    -0.06
     zvyš
    -0.06
     lawmakers
    -0.05
     gì
    -0.05
    ウェ
    -0.05
    POSITIVE LOGITS
    _callable
    0.08
    _aut
    0.07
    τια
    0.07
     spis
    0.07
     Original
    0.07
    Result
    0.07
    Unified
    0.06
    (asset
    0.06
    _PROVIDER
    0.06
    струмент
    0.06
    Act Density 0.017%

    No Known Activations