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

    Neuronpedia

    INDEX
    Explanations

    Negative situations/complaints

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مشين
    -0.67
    Tikang
    -0.57
    enação
    -0.52
    AsUp
    -0.52
    routeProvider
    -0.50
    ItemBackground
    -0.49
     Signalez
    -0.48
     beginnetje
    -0.48
    رشف
    -0.47
     båda
    -0.47
    POSITIVE LOGITS
    NewUrlParser
    0.55
     NDEBUG
    0.52
     برانيه
    0.52
    خان
    0.51
    setupUi
    0.51
     ute
    0.50
     hidden
    0.50
     cre
    0.49
    MoveTo
    0.49
    thian
    0.48
    Act Density 0.003%

    No Known Activations