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

    Neuronpedia

    INDEX
    Explanations

    scientific publication references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .dependencies
    -0.07
     offline
    -0.06
    /of
    -0.06
     �
    -0.06
    ับม
    -0.06
    convert
    -0.06
    \",\
    -0.06
     slack
    -0.06
    tags
    -0.06
    Mappings
    -0.06
    POSITIVE LOGITS
     Ghana
    0.07
     �
    0.07
    felt
    0.07
    uguay
    0.07
     segmented
    0.07
    ادا
    0.06
    erre
    0.06
     preprocess
    0.06
    ичної
    0.06
     Herb
    0.06
    Act Density 0.019%

    No Known Activations