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

    Neuronpedia

    INDEX
    Explanations

    terms of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    b
    0.58
    p
    0.57
    类似于
    0.55
    m
    0.55
     selben
    0.52
     ενός
    0.50
    H
    0.50
    pano
    0.49
    ird
    0.49
    eleng
    0.48
    POSITIVE LOGITS
    TOO
    0.53
    道具
    0.52
     mídia
    0.52
     consomm
    0.51
     residuos
    0.51
     consumo
    0.50
    ח
    0.49
     hielo
    0.49
     fuente
    0.49
     minuman
    0.49
    Act Density 0.006%

    No Known Activations