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

    Neuronpedia

    INDEX
    Explanations

    common phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     isn
    1.30
     doesn
    1.24
     একটা
    1.22
    有点
    1.19
     outro
    1.18
    У
    1.14
     Essa
    1.13
    И
    1.13
     geeft
    1.12
     wasn
    1.12
    POSITIVE LOGITS
     themselves
    1.84
    各自
    1.70
    selves
    1.63
    纷纷
    1.60
     бъдат
    1.58
    jų
    1.55
     مراکز
    1.49
     जिनमें
    1.48
    timeslots
    1.46
     ತಮ್ಮ
    1.45
    Act Density 0.136%

    No Known Activations