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

    Neuronpedia

    INDEX
    Explanations

    academic journal citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    posite
    0.38
    irlo
    0.38
    吹き
    0.36
     বোনের
    0.35
    ायला
    0.35
    swa
    0.35
    吧
    0.35
     کنید
    0.34
    upy
    0.34
     minder
    0.34
    POSITIVE LOGITS
     Laden
    0.42
    雑誌
    0.41
     জীববিজ্ঞান
    0.41
     সহানুভূতি
    0.39
    ած
    0.38
    潞
    0.37
     उत्ते
    0.37
     journal
    0.37
     أبريل
    0.35
     журнал
    0.35
    Act Density 0.003%

    No Known Activations