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

    Neuronpedia

    INDEX
    Explanations

    upon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     varandra
    -0.71
    findpost
    -0.65
     difesa
    -0.56
    UserScript
    -0.56
     culturelles
    -0.56
     hendes
    -0.54
     juridiques
    -0.54
     bonté
    -0.54
     sonho
    -0.54
     sauvages
    -0.54
    POSITIVE LOGITS
     Metro
    0.47
     Northern
    0.46
    sty
    0.46
     Greater
    0.46
     we
    0.44
     للاسماء
    0.44
     South
    0.43
    లాలు
    0.43
     on
    0.43
    Enllaces
    0.43
    Act Density 0.001%

    No Known Activations