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

    Neuronpedia

    INDEX
    Explanations

    common request dictionary mapping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     جوړونکی
    0.47
    ஷா
    0.45
    са
    0.44
     три
    0.44
    ༞
    0.44
    ஸ்க
    0.43
    ními
    0.42
    тор
    0.42
     راجس
    0.42
    он
    0.41
    POSITIVE LOGITS
    K
    0.52
     ziehen
    0.47
    GetChar
    0.46
    ue
    0.46
     かわいい
    0.45
    S
    0.44
    leq
    0.44
    Command
    0.44
     Command
    0.44
    Leod
    0.44
    Act Density 0.002%

    No Known Activations