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

    Neuronpedia

    INDEX
    Explanations

    ism

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .getValue
    -0.08
    COVER
    -0.07
    游戏副本
    -0.07
    IBLE
    -0.07
    .WebServlet
    -0.07
    .part
    -0.07
    里面的
    -0.07
    season
    -0.06
     Financial
    -0.06
     David
    -0.06
    POSITIVE LOGITS
    靓
    0.08
     autism
    0.08
    🎉
    0.07
    钦
    0.07
     working
    0.07
    働き
    0.07
    违
    0.07
    东营
    0.07
     �
    0.07
    0.06
    Act Density 0.002%

    No Known Activations