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

    Neuronpedia

    INDEX
    Explanations

    balance and organize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     restrooms
    0.41
     lako
    0.40
     ventilators
    0.40
     motivator
    0.40
    楨
    0.40
    opters
    0.39
     axles
    0.39
     locomotives
    0.39
     motivated
    0.39
     motivating
    0.38
    POSITIVE LOGITS
     έναν
    0.45
     στι
    0.42
     שני
    0.40
    answ
    0.39
     γεν
    0.39
     Brug
    0.39
     βαθ
    0.38
    watch
    0.37
    ński
    0.36
    Ring
    0.36
    Act Density 0.003%

    No Known Activations