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

    Neuronpedia

    INDEX
    Explanations

    dom

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    favorite
    -0.07
     pipeline
    -0.07
    _thumb
    -0.07
     Чем
    -0.07
     fixture
    -0.07
     antibiotic
    -0.06
    　　　　 　
    -0.06
     utterly
    -0.06
    thumb
    -0.06
     renown
    -0.06
    POSITIVE LOGITS
    ô
    0.07
     Hell
    0.07
    fox
    0.06
    rolling
    0.06
     glEnable
    0.06
    ой
    0.06
     cread
    0.06
    .Dir
    0.06
    自
    0.06
    XY
    0.06
    Act Density 0.004%

    No Known Activations