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

    Neuronpedia

    INDEX
    Explanations

    real-world contexts and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    کو
    0.68
    凖
    0.67
    ámico
    0.65
    toadd
    0.64
    toISO
    0.63
    setNome
    0.62
    俔
    0.62
    okban
    0.61
    range
    0.60
    texto
    0.60
    POSITIVE LOGITS
    s
    0.82
    ;
    0.65
    C
    0.62
     prowess
    0.58
    ุ
    0.58
    ,
    0.57
    B
    0.56
    对于
    0.55
     demikian
    0.55
    ed
    0.54
    Act Density 0.008%

    No Known Activations