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

    Neuronpedia

    INDEX
    Explanations

    detection and measurement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	opt
    -0.07
    ComboBox
    -0.06
    海道
    -0.06
    陵
    -0.06
     봐
    -0.06
     Mit
    -0.06
     Grape
    -0.06
     Filtering
    -0.06
    軽
    -0.06
     caratter
    -0.06
    POSITIVE LOGITS
    959
    0.07
    fef
    0.06
    ,id
    0.06
     ALIGN
    0.06
    idlo
    0.06
    μοί
    0.06
    ्रब
    0.06
     darken
    0.06
    uracion
    0.06
     word
    0.06
    Act Density 0.172%

    No Known Activations