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

    Neuronpedia

    INDEX
    Explanations

    tradition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Disco
    -0.26
    é¢Ĩè¡Ķ
    -0.26
     {}č↵
    -0.26
     Naughty
    -0.25
    ä¼ļ让
    -0.25
     GÅĤ
    -0.24
    éĴŁ
    -0.24
    sted
    -0.24
    airy
    -0.24
    ç«ł
    -0.24
    POSITIVE LOGITS
    รà¸Ńย
    0.27
     intending
    0.26
    ien
    0.25
    ãĤªãĥ³
    0.24
     accord
    0.24
    rnd
    0.24
    iane
    0.24
    çĶŁäºİ
    0.24
     meant
    0.23
     smooth
    0.23
    Act Density 0.021%

    No Known Activations