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

    Neuronpedia

    INDEX
    Explanations

    US or Hero

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     نیاز
    0.48
    adple
    0.48
    latency
    0.48
    น่า
    0.47
    บน
    0.47
    periodic
    0.46
    ymptotic
    0.46
    incar
    0.46
    isLen
    0.46
    astere
    0.46
    POSITIVE LOGITS
    ס
    0.52
     options
    0.48
    বসাইটে
    0.48
     allocations
    0.47
     classes
    0.46
     canisters
    0.46
     additions
    0.46
    ות
    0.45
     shoulders
    0.45
     Substit
    0.45
    Act Density 0.000%

    No Known Activations