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

    Neuronpedia

    INDEX
    Explanations

    code blocks or structured text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Human
    0.62
     Triple
    0.61
    ric
    0.60
    lau
    0.59
     triple
    0.59
    LetterIndex
    0.58
    Triple
    0.58
     human
    0.58
     dot
    0.58
     indoors
    0.57
    POSITIVE LOGITS
    ńst
    0.61
    atera
    0.61
    ಾಸ
    0.61
    tní
    0.60
     master
    0.59
    াণ
    0.59
     Master
    0.57
    <unused420>
    0.56
    ಟರ್
    0.56
    isem
    0.56
    Act Density 0.190%

    No Known Activations