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

    Neuronpedia

    INDEX
    Explanations

    abstractive and extractive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Número
    0.46
     sme
    0.46
    សម
    0.46
    Uz
    0.44
     Vereinig
    0.44
    Turbo
    0.43
     réduction
    0.42
    Samuel
    0.42
     reicht
    0.42
    geht
    0.41
    POSITIVE LOGITS
    oglio
    0.42
     आफ्
    0.42
     infall
    0.41
     arrhythmias
    0.41
     వివా
    0.40
    graphicx
    0.39
    💾
    0.39
    $~
    0.39
    仲間
    0.39
     짜
    0.38
    Act Density 0.000%

    No Known Activations