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

    Neuronpedia

    INDEX
    Explanations

    finding product or understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     partage
    0.46
    TaskId
    0.44
     ሁሉም
    0.43
     voire
    0.42
    리에
    0.42
    льне
    0.42
     ተመሳሳይ
    0.42
     ይህም
    0.40
     musculaire
    0.40
    വില്‍
    0.39
    POSITIVE LOGITS
    itzerland
    0.48
    atz
    0.44
    ißler
    0.43
    rijven
    0.43
     crypt
    0.42
    udit
    0.41
    闢
    0.41
    åk
    0.41
     logits
    0.40
    quare
    0.40
    Act Density 0.001%

    No Known Activations