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

    Neuronpedia

    INDEX
    Explanations

    Ephesians keto Flatten

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    で
    0.51
    beqz
    0.47
    積極的に
    0.46
    Secondo
    0.46
    ².
    0.45
     ejecut
    0.45
     cedo
    0.45
     अन्यथा
    0.44
     dengan
    0.44
    工作室
    0.44
    POSITIVE LOGITS
    alne
    0.45
    State
    0.42
     kolejne
    0.42
    Status
    0.41
    باد
    0.39
    Location
    0.39
    atae
    0.38
    бята
    0.38
    arynx
    0.38
    uola
    0.38
    Act Density 0.003%

    No Known Activations