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

    Neuronpedia

    INDEX
    Explanations

    websites and official sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     button
    0.43
     DA
    0.39
     жөн
    0.39
    人と
    0.38
     add
    0.37
    <unused61>
    0.37
     gull
    0.37
     da
    0.36
     seal
    0.36
     dao
    0.36
    POSITIVE LOGITS
    žić
    0.41
     Así
    0.40
     ″
    0.39
     évén
    0.39
     ప్రజా
    0.38
     “,
    0.37
    ″
    0.37
    κος
    0.37
    ⴱ
    0.37
     dilwale
    0.37
    Act Density 0.000%

    No Known Activations