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

    Neuronpedia

    INDEX
    Explanations

    //

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     도시
    -0.07
    shouldBe
    -0.07
    ducer
    -0.06
     디자인
    -0.06
    *)↵↵
    -0.06
     verdiği
    -0.06
     Cette
    -0.06
    لح
    -0.06
    .TextUtils
    -0.06
    (and
    -0.06
    POSITIVE LOGITS
    orrect
    0.07
    irm
    0.07
    вать
    0.07
     explo
    0.07
     civilized
    0.07
     placeholders
    0.06
    fed
    0.06
     Например
    0.06
     wrappers
    0.06
    affle
    0.06
    Act Density 0.001%

    No Known Activations