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

    Neuronpedia

    INDEX
    Explanations

    let followed by me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    क्साइड
    0.65
     업
    0.55
    by
    0.54
    メイン
    0.54
    લિ
    0.53
     απο
    0.53
    ક્
    0.53
     글
    0.52
     চীনা
    0.52
    ंती
    0.51
    POSITIVE LOGITS
     welfare
    0.69
     whites
    0.69
     ventures
    0.67
     sobą
    0.64
     white
    0.63
     forests
    0.63
     stand
    0.63
     economic
    0.63
     bosom
    0.62
     areas
    0.61
    Act Density 0.000%

    No Known Activations