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

    Neuronpedia

    INDEX
    Explanations

    challenge, client, patient, last

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    是很
    1.30
     essentielles
    1.27
     brillantes
    1.20
    फॉ
    1.13
     vitaminas
    1.12
     diğer
    1.11
    transferases
    1.10
    리오
    1.09
     duquel
    1.09
     grasses
    1.09
    POSITIVE LOGITS
    ம்
    1.29
    aient
    1.03
    ור
    1.00
    ו
    0.96
    িন
    0.95
    ार
    0.94
    ون
    0.91
    ל
    0.91
    jahr
    0.90
    ০১
    0.88
    Act Density 0.000%

    No Known Activations