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

    Neuronpedia

    INDEX
    Explanations

    string manipulation functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     activists
    0.44
     protesters
    0.41
     requisite
    0.39
     preexisting
    0.38
     parametr
    0.38
     compositional
    0.38
    vvvert
    0.38
     sponsors
    0.37
     optically
    0.37
     täht
    0.37
    POSITIVE LOGITS
     San
    0.47
    San
    0.46
    rei
    0.43
    Rain
    0.42
     hasn
    0.42
    Сан
    0.42
     sano
    0.41
    compare
    0.41
    شاء
    0.40
    बाई
    0.39
    Act Density 0.000%

    No Known Activations