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

    Neuronpedia

    INDEX
    Explanations

    price ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sixty
    1.23
     eighty
    1.22
     eight
    1.20
     seventy
    1.19
     nine
    1.16
     ۹
    1.15
     ninety
    1.15
     seven
    1.11
     ८
    1.11
     forty
    1.09
    POSITIVE LOGITS
    log
    0.72
    य़ा
    0.70
    TXT
    0.69
    observ
    0.67
    index
    0.66
    Ds
    0.63
    val
    0.62
    RB
    0.62
    чества
    0.61
    သောအ
    0.61
    Act Density 0.199%

    No Known Activations