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

    Neuronpedia

    INDEX
    Explanations

    explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Flick
    0.46
     ic
    0.45
     observ
    0.43
    lij
    0.43
     flick
    0.41
     Rican
    0.41
     TIC
    0.39
     Kinder
    0.39
     electing
    0.39
     Kam
    0.39
    POSITIVE LOGITS
    appelijke
    0.44
    autoprefixer
    0.41
     ResponseEntity
    0.41
     núcle
    0.40
    istere
    0.39
    Biz
    0.39
    百家乐
    0.39
     trueMap
    0.39
    FUENTE
    0.38
    ServiceImpl
    0.38
    Act Density 0.000%

    No Known Activations