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

    Neuronpedia

    INDEX
    Explanations

    transformers, loading models

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Enabled
    -0.07
    Surv
    -0.06
     vanilla
    -0.06
     weighed
    -0.06
    cn
    -0.06
     south
    -0.06
             ↵
    -0.06
     buttons
    -0.06
    fore
    -0.06
    ném
    -0.06
    POSITIVE LOGITS
    HeadersHeightSizeMode
    0.07
    prü
    0.07
    に行
    0.07
    _WRONG
    0.06
     Goddess
    0.06
    .work
    0.06
    自动
    0.06
     borderTop
    0.06
    945
    0.06
    .setBackgroundColor
    0.06
    Act Density 0.003%

    No Known Activations