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

    Neuronpedia

    INDEX
    Explanations

    fonts, colours, layout

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resonances
    0.34
     sombras
    0.32
     usar
    0.32
     solicitudes
    0.32
     distinguer
    0.31
     isoforms
    0.31
     subcut
    0.31
     vitesses
    0.31
     voltages
    0.30
     tamaños
    0.30
    POSITIVE LOGITS
     ความ
    0.34
    analyse
    0.32
    Analyze
    0.30
     कृष्णा
    0.30
    <unused2040>
    0.29
     Cryptocurrency
    0.29
    更加
    0.28
    Authenticate
    0.28
    instagood
    0.28
    analisi
    0.28
    Act Density 1.573%

    No Known Activations