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

    Neuronpedia

    INDEX
    Explanations

    messes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    狺
    -0.07
    ılması
    -0.07
    看得
    -0.07
     применения
    -0.07
    Sk
    -0.07
    asyarakat
    -0.07
     powerless
    -0.07
    ⊅
    -0.06
     eldre
    -0.06
     collision
    -0.06
    POSITIVE LOGITS
    农民工
    0.07
    大局
    0.07
    乡土
    0.07
    福祉
    0.07
     finals
    0.07
    🎂
    0.07
    桐
    0.07
    팁
    0.07
     Democrat
    0.07
    WS
    0.07
    Act Density 0.037%

    No Known Activations