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

    Neuronpedia

    INDEX
    Explanations

    ratings or qualifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iv
    0.47
    ล
    0.45
     I
    0.44
     নিরস্ত্র
    0.42
    ივ
    0.42
    ડ
    0.42
     ราย
    0.40
     Noeud
    0.39
    linen
    0.39
     armband
    0.39
    POSITIVE LOGITS
    цев
    0.46
    спублі
    0.45
    bid
    0.45
     calificaciones
    0.44
     traditional
    0.43
     इसके
    0.43
     социа
    0.43
     परसेंटेज
    0.43
    chte
    0.42
     marketed
    0.42
    Act Density 0.008%

    No Known Activations