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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    issue
    -0.07
    受访
    -0.07
     Managing
    -0.07
    Seleccione
    -0.07
    底气
    -0.07
    .tracks
    -0.07
     הוד
    -0.06
     Weekly
    -0.06
    /Game
    -0.06
     Recogn
    -0.06
    POSITIVE LOGITS
    Pu
    0.07
    stants
    0.06
     inappropriate
    0.06
    isons
    0.06
    _HOLD
    0.06
    CppMethod
    0.06
     trabalho
    0.06
    太
    0.06
    坑
    0.06
    霪
    0.06
    Act Density 0.003%

    No Known Activations