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

    Neuronpedia

    INDEX
    Explanations

    ak

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     localized
    -0.07
    �
    -0.07
     �
    -0.06
     serta
    -0.06
    .ResponseBody
    -0.06
     testers
    -0.06
     denně
    -0.06
    grese
    -0.06
    .dumps
    -0.06
    _cr
    -0.06
    POSITIVE LOGITS
    .shortcuts
    0.07
    Рµ
    0.07
     Kew
    0.07
    kick
    0.07
    Guest
    0.06
    -hidden
    0.06
    wine
    0.06
    SqlParameter
    0.06
    �
    0.06
     baktı
    0.06
    Act Density 0.008%

    No Known Activations