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

    Neuronpedia

    INDEX
    Explanations

    month in dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ह्म
    0.47
    JScripts
    0.44
    %$$
    0.43
    Cla
    0.42
    ス
    0.40
     ਜਾ
    0.40
     천
    0.40
     スマ
    0.40
     edificio
    0.39
     দে
    0.39
    POSITIVE LOGITS
    liert
    0.41
     hands
    0.40
    mais
    0.40
     Jetty
    0.38
     Heated
    0.37
     Training
    0.37
    elson
    0.36
     permissive
    0.36
     offering
    0.36
     null
    0.36
    Act Density 0.002%

    No Known Activations