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

    Neuronpedia

    INDEX
    Explanations

    your kind words and affection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    se
    0.48
     manchas
    0.45
    um
    0.45
    eln
    0.45
    ulfite
    0.45
    apr
    0.43
    ll
    0.43
    ozyg
    0.42
    ana
    0.42
    ap
    0.42
    POSITIVE LOGITS
     капитала
    0.50
     היה
    0.48
     архі
    0.46
     постав
    0.46
     столи
    0.46
     تث
    0.45
     ת
    0.43
     עי
    0.43
    Пре
    0.42
    ยาว
    0.42
    Act Density 0.013%

    No Known Activations