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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Foods
    0.49
     Idani
    0.48
     Herbs
    0.47
     poisons
    0.47
     Malibu
    0.47
     Ritual
    0.45
     Checks
    0.45
     Cách
    0.45
     নৌকা
    0.45
    នៅលើ
    0.45
    POSITIVE LOGITS
    र्घ
    0.54
    S
    0.54
     aseg
    0.52
    프
    0.48
    ερ
    0.48
    7
    0.48
    𝗴
    0.48
    าค
    0.47
    ص
    0.47
    frac
    0.47
    Act Density 0.000%

    No Known Activations