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

    Neuronpedia

    INDEX
    Explanations

    parsing data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    recommended
    0.48
    b
    0.48
    t
    0.47
    uploader
    0.46
    i
    0.46
    larında
    0.45
    Juris
    0.44
    SESSION
    0.44
    BLO
    0.44
    Translator
    0.44
    POSITIVE LOGITS
     parses
    0.63
     Parse
    0.59
     解析
    0.59
     Pars
    0.54
     Parses
    0.54
     parsley
    0.52
     Parser
    0.52
     into
    0.52
     Parsing
    0.50
    FromString
    0.48
    Act Density 0.005%

    No Known Activations