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

    Neuronpedia

    INDEX
    Explanations

    major powers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atoi
    0.51
    ikia
    0.51
    ua
    0.45
    ombra
    0.44
    ਸ਼ਨ
    0.44
    rende
    0.43
    ymology
    0.43
    usia
    0.43
    iska
    0.42
    ueda
    0.42
    POSITIVE LOGITS
    嵃
    0.52
    沚
    0.52
    ্রো
    0.50
     outputs
    0.48
    িনবার্গ
    0.48
     autorità
    0.46
     hiện
    0.46
    中国
    0.45
     così
    0.44
    າດ
    0.44
    Act Density 0.000%

    No Known Activations