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

    Neuronpedia

    INDEX
    Explanations

    February

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sabe
    -0.07
    Leg
    -0.07
    wind
    -0.06
    Stand
    -0.06
    _markers
    -0.06
     snd
    -0.06
    awa
    -0.06
     쿠
    -0.06
     Tib
    -0.06
     Sloven
    -0.06
    POSITIVE LOGITS
    们
    0.06
    bruary
    0.06
     imread
    0.06
     Curriculum
    0.06
    lıklı
    0.06
    věř
    0.06
    _MethodInfo
    0.06
    79
    0.06
    -reset
    0.06
    ิย
    0.06
    Act Density 0.018%

    No Known Activations