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

    Neuronpedia

    INDEX
    Explanations

    reach a wider audience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ре
    0.84
     изображение
    0.80
     опла
    0.79
     стране
    0.79
     строительство
    0.79
     αποτέ
    0.78
    ﻧ
    0.78
    <0x04>
    0.77
     мнение
    0.77
    vá
    0.75
    POSITIVE LOGITS
    al
    1.17
    ,
    1.05
     reach
    1.00
     reaches
    0.91
    in
    0.89
    は
    0.88
    د
    0.86
    os
    0.83
    س
    0.82
    s
    0.80
    Act Density 0.019%

    No Known Activations