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

    Neuronpedia

    INDEX
    Explanations

    completing phrases and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ald
    0.49
    Albert
    0.47
    Alfred
    0.47
    Aston
    0.47
    Candy
    0.46
    捒
    0.46
    Tint
    0.46
    Hart
    0.44
    College
    0.44
    Mount
    0.44
    POSITIVE LOGITS
    ۆ
    0.51
    تی
    0.50
    subscribed
    0.49
    epte
    0.49
    ália
    0.48
     Bereich
    0.47
    نتی
    0.46
    upyter
    0.46
    ンの
    0.46
    ವುದು
    0.44
    Act Density 0.002%

    No Known Activations