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

    Neuronpedia

    INDEX
    Explanations

    favoring specific candidates or outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     loyal
    0.43
     independ
    0.41
     Shares
    0.39
     Zugang
    0.39
     returning
    0.39
     brig
    0.39
     facing
    0.38
     Woodford
    0.38
     Trin
    0.38
     odpowied
    0.38
    POSITIVE LOGITS
    Cir
    0.44
    prote
    0.43
     प्रतिदिन
    0.40
    Chron
    0.40
     Recreational
    0.39
    jarige
    0.39
    istemas
    0.39
    晛
    0.39
    icot
    0.39
    onChange
    0.39
    Act Density 0.000%

    No Known Activations