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

    Neuronpedia

    INDEX
    Explanations

    mathematical theorems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thermometer
    -0.09
    heit
    -0.08
     percentile
    -0.08
     marketing
    -0.07
    케팅
    -0.07
     eviction
    -0.07
     tailoring
    -0.07
     household
    -0.07
     biomass
    -0.07
     positioning
    -0.07
    POSITIVE LOGITS
     magk
    0.09
     tric
    0.08
     sacred
    0.08
    保存
    0.08
     salvar
    0.08
    �
    0.08
     dancers
    0.08
     reger
    0.08
     reunir
    0.08
    save
    0.08
    Act Density 0.019%

    No Known Activations