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

    Neuronpedia

    INDEX
    Explanations

    commands and code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    हे
    0.74
    Ѕ
    0.65
    క్ర
    0.62
     Le
    0.61
     CHARSET
    0.60
     заку
    0.60
     uniform
    0.59
    gher
    0.59
    द्धांत
    0.58
     फार
    0.58
    POSITIVE LOGITS
     ใจ
    0.75
    娠
    0.68
    บท
    0.68
    льні
    0.66
    ivities
    0.65
    情緒
    0.64
    토리
    0.64
     บท
    0.63
     dr
    0.63
    ionych
    0.62
    Act Density 0.209%

    No Known Activations