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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrase pairings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ems
    0.41
     활용
    0.40
    ̨
    0.40
     opportunistic
    0.38
    eme
    0.38
     객
    0.38
    hao
    0.37
    atan
    0.37
    rames
    0.36
    le
    0.36
    POSITIVE LOGITS
    欵
    0.43
     även
    0.43
     것도
    0.41
     Motorsport
    0.40
     Cattle
    0.38
    これも
    0.38
    ைகளும்
    0.38
     тоже
    0.37
     واقف
    0.37
     promo
    0.37
    Act Density 0.000%

    No Known Activations