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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ottesville
    0.38
    DepartTime
    0.38
    ünü
    0.37
    ष्टमी
    0.37
    ماية
    0.37
    osiery
    0.37
    ᒪ
    0.37
    েরা
    0.36
    ."'
    0.36
    简称
    0.36
    POSITIVE LOGITS
     V
    0.45
     S
    0.38
     il
    0.38
     de
    0.37
     SU
    0.36
     RAM
    0.36
     bess
    0.35
     $,
    0.35
     OF
    0.35
     TR
    0.35
    Act Density 0.007%

    No Known Activations