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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     casts
    0.45
    িতা
    0.37
    iejęt
    0.37
    ائیگی
    0.36
     completa
    0.36
     enum
    0.34
    Subs
    0.34
    ariy
    0.34
     intensidad
    0.34
    Presence
    0.33
    POSITIVE LOGITS
     flea
    0.46
     politely
    0.46
    यान
    0.45
     cellar
    0.42
     corrugated
    0.41
    agrave
    0.41
     attic
    0.40
    $-$,
    0.40
    atcher
    0.39
    unpriv
    0.39
    Act Density 0.000%

    No Known Activations