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

    Neuronpedia

    INDEX
    Explanations

    complex topics and situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    figsize
    0.46
    เหมาะ
    0.45
    сант
    0.45
    ATER
    0.44
    দর
    0.44
    잽
    0.44
    開催
    0.44
    ته
    0.43
    LCM
    0.43
    eszcze
    0.42
    POSITIVE LOGITS
    i
    0.60
    ي
    0.56
    ;
    0.51
    rían
    0.49
    polyfill
    0.45
     coexist
    0.44
     POL
    0.44
     fraternal
    0.44
     composers
    0.43
     получают
    0.41
    Act Density 0.001%

    No Known Activations