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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hatch
    -0.08
    ,,
    -0.07
     �
    -0.07
    >
↵
    -0.07
     radioButton
    -0.06
     множе
    -0.06
    alizace
    -0.06
     queer
    -0.06
    progressbar
    -0.06
     Language
    -0.06
    POSITIVE LOGITS
    roj
    0.07
    =dict
    0.06
    edef
    0.06
    _tolerance
    0.06
    asic
    0.06
     같습니다
    0.06
    였다
    0.06
     junk
    0.06
    woke
    0.06
    私
    0.06
    Act Density 0.001%

    No Known Activations