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

    Neuronpedia

    INDEX
    Explanations

    abstract noun phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     forgo
    0.50
     送料無料
    0.50
    お店
    0.50
     glum
    0.48
    3
    0.48
     hapless
    0.47
     fit
    0.46
    ")){
    0.46
     mindless
    0.46
    f
    0.45
    POSITIVE LOGITS
     स्टेशनों
    0.53
     comunicaciones
    0.52
    microseconds
    0.52
    推广
    0.51
    ่น
    0.48
    Methylsulfanyl
    0.48
    禳
    0.48
     montaje
    0.48
    涳
    0.47
    וק
    0.47
    Act Density 0.000%

    No Known Activations