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

    Neuronpedia

    INDEX
    Explanations

    list categories and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     expend
    0.53
     compromise
    0.52
     immobil
    0.50
    로
    0.49
     immobile
    0.46
    cri
    0.46
     the
    0.46
     tenho
    0.45
     иностран
    0.45
     extremely
    0.44
    POSITIVE LOGITS
    敨
    0.46
     標準
    0.45
    <unused82>
    0.45
    <unused42>
    0.44
    <unused27>
    0.44
    我们要
    0.44
    <unused43>
    0.44
    ائیگی
    0.43
     மொத்தம்
    0.43
    抺
    0.43
    Act Density 0.001%

    No Known Activations