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

    Neuronpedia

    INDEX
    Explanations

    SQuAD, SBR, SAAMI, Sentry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ocles
    0.40
     imm
    0.39
    Imm
    0.39
    diagn
    0.38
    ალური
    0.38
    angan
    0.38
    worthiness
    0.37
    ंत्रिकी
    0.37
    ovod
    0.37
     CCCC
    0.37
    POSITIVE LOGITS
    Myers
    0.48
     Myers
    0.42
     Meyers
    0.41
     Sauer
    0.41
     steht
    0.40
    unie
    0.39
     liegt
    0.38
     uncut
    0.38
     kleines
    0.38
    وي
    0.37
    Act Density 0.004%

    No Known Activations