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

    Neuronpedia

    INDEX
    Explanations

    Scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     عکس
    -0.07
     Це
    -0.07
     않았
    -0.07
     двад
    -0.06
    	file
    -0.06
    firebase
    -0.06
     Praze
    -0.06
    の一
    -0.06
     千
    -0.06
    вает
    -0.06
    POSITIVE LOGITS
     suggest
    0.07
     fertil
    0.07
    \Response
    0.06
    567
    0.06
     модели
    0.06
     látky
    0.06
     Cleveland
    0.06
    esa
    0.06
    _watch
    0.06
     separates
    0.06
    Act Density 0.210%

    No Known Activations