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

    Neuronpedia

    INDEX
    Explanations

    after that happened

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ida
    0.57
    ipa
    0.49
     Hask
    0.48
    ia
    0.48
    isk
    0.47
    iao
    0.47
    iban
    0.46
    ahoo
    0.46
    ipy
    0.46
    iana
    0.45
    POSITIVE LOGITS
    쐞
    0.50
     ого
    0.48
     आरओ
    0.48
    UILLER
    0.47
    FOR
    0.42
    を持つ
    0.42
     של
    0.41
    エンジ
    0.41
    스의
    0.41
     када
    0.41
    Act Density 0.001%

    No Known Activations