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

    Neuronpedia

    INDEX
    Explanations

    author, book, citation details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ie
    0.52
    stri
    0.52
    !’
    0.48
    ía
    0.47
    Prevention
    0.46
    atia
    0.46
    ogr
    0.45
    CCO
    0.45
    acca
    0.45
    oja
    0.45
    POSITIVE LOGITS
    म्यान
    0.53
    เฉพาะ
    0.53
    ต
    0.50
    नंतर
    0.50
    सात
    0.50
    дал
    0.49
    オーナー
    0.49
     Volkswagen
    0.49
    大战
    0.48
     บวก
    0.47
    Act Density 0.000%

    No Known Activations