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

    Neuronpedia

    INDEX
    Explanations

    acutely aware of something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ת
    0.96
    ia
    0.92
    ט
    0.88
    ная
    0.86
    ap
    0.84
    ta
    0.84
    িন
    0.84
    ク
    0.84
    ടി
    0.84
    امي
    0.83
    POSITIVE LOGITS
     keenly
    0.84
    lere
    0.84
     keen
    0.82
     violinist
    0.77
     зрения
    0.77
     ότι
    0.75
    ?
    0.73
     pelvis
    0.72
    ล์
    0.71
     gerente
    0.71
    Act Density 0.005%

    No Known Activations