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

    Neuronpedia

    INDEX
    Explanations

    specializing in minors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StringBuilder
    0.66
    íram
    0.65
     Figma
    0.64
     ϒ
    0.63
    silyl
    0.63
     орби
    0.63
     构建
    0.63
    vDash
    0.63
    cosystem
    0.62
    getConfig
    0.62
    POSITIVE LOGITS
     eben
    0.67
    .
    0.66
     परन्तु
    0.64
     same
    0.63
     but
    0.63
     namun
    0.62
     being
    0.61
     misma
    0.60
     wre
    0.59
     presented
    0.59
    Act Density 0.123%

    No Known Activations