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

    Neuronpedia

    INDEX
    Explanations

    static cast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    阿里
    0.57
     carénés
    0.56
    비스
    0.55
    이버
    0.55
     Ві
    0.55
    프트
    0.54
    이브
    0.54
    ilibus
    0.54
    Celltype
    0.54
    hankelijk
    0.54
    POSITIVE LOGITS
    s
    0.78
    in
    0.65
     at
    0.61
     dollars
    0.61
    sh
    0.60
     t
    0.59
    sum
    0.58
     mirror
    0.57
     is
    0.56
     thickness
    0.56
    Act Density 0.000%

    No Known Activations