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

    Neuronpedia

    INDEX
    Explanations

    special characters and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Siegel
    0.44
     teş
    0.41
     الحاج
    0.41
     sieve
    0.40
     [§
    0.39
    ূর্তি
    0.39
    eyen
    0.38
     Auger
    0.38
    𓏧
    0.38
    ětí
    0.38
    POSITIVE LOGITS
    િવ
    0.41
     γ
    0.40
    γ
    0.37
    換
    0.37
     गामा
    0.37
    เพียง
    0.36
    换
    0.36
     mild
    0.35
     garantías
    0.35
     cola
    0.35
    Act Density 0.001%

    No Known Activations