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

    Neuronpedia

    INDEX
    Explanations

    free distribution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    code
    0.50
     '
    0.47
     becomes
    0.45
    ed
    0.45
    En
    0.45
     code
    0.44
    def
    0.43
    en
    0.43
    api
    0.43
    fo
    0.42
    POSITIVE LOGITS
    }^{+},
    0.47
    幷
    0.42
    റും
    0.41
     Ανακτήθηκε
    0.41
    髹
    0.41
     ننوت
    0.41
    欬
    0.41
     verschied
    0.40
     ไหร่
    0.40
    踌
    0.40
    Act Density 0.004%

    No Known Activations