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

    Neuronpedia

    INDEX
    Explanations

    my followed by medical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    то
    0.84
    ре
    0.79
    ра
    0.79
    et
    0.76
    (
    0.75
    ీ
    0.74
    <0x80>
    0.73
    ాన్
    0.72
    с
    0.71
    <0x91>
    0.71
    POSITIVE LOGITS
    อย่าง
    0.67
     as
    0.66
    bilisi
    0.65
    גה
    0.63
    i
    0.60
    ڈ
    0.60
     รวมถึง
    0.59
     ,
    0.57
    کو
    0.56
     esclusivamente
    0.56
    Act Density 0.004%

    No Known Activations