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

    Neuronpedia

    INDEX
    Explanations

    based on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iquée
    0.44
    ături
    0.44
     разнообраз
    0.43
     Banyak
    0.41
     banyak
    0.40
     பார்
    0.40
    ácil
    0.40
     lớ
    0.40
     ලද
    0.40
    лення
    0.39
    POSITIVE LOGITS
     requesting
    0.41
     درخواست
    0.38
    ঞ
    0.38
    either
    0.38
     fatorial
    0.38
    requests
    0.36
    endpoints
    0.36
    aio
    0.36
     unusual
    0.36
     request
    0.36
    Act Density 0.000%

    No Known Activations