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

    Neuronpedia

    INDEX
    Explanations

    resistance to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PlayerSelector
    0.49
    لي
    0.45
    سک
    0.44
    經
    0.42
    haya
    0.41
    𒆜
    0.41
    ح
    0.41
    旯
    0.41
    洊
    0.41
     resonators
    0.40
    POSITIVE LOGITS
     resist
    0.49
     put
    0.46
    ANIEL
    0.46
     শুভ
    0.44
    trend
    0.44
    airy
    0.42
     fiercely
    0.42
    ad
    0.41
     temptation
    0.40
     OutputStream
    0.40
    Act Density 0.013%

    No Known Activations