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

    Neuronpedia

    INDEX
    Explanations

    various usages of `close`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     रतन
    0.46
     标准
    0.43
     Над
    0.41
     Plenum
    0.40
     Byte
    0.39
    वेदन
    0.39
     Результа
    0.38
    〝
    0.38
     meticulous
    0.38
    啖
    0.38
    POSITIVE LOGITS
    augment
    0.40
     magari
    0.39
     ben
    0.38
    tera
    0.38
     المقدس
    0.37
     Majesty
    0.37
     ext
    0.36
     schweren
    0.36
     dign
    0.36
     dignit
    0.36
    Act Density 0.001%

    No Known Activations