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

    Neuronpedia

    INDEX
    Explanations

    words that indicate categories, activities, or organizations

    oai_token-act-pair · gemini-2.0-flash

    sport

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    culo
    -0.49
    kreis
    -0.48
     suc
    -0.46
    cules
    -0.46
    mulo
    -0.45
    ForValue
    -0.45
    ági
    -0.42
    kräf
    -0.42
    olé
    -0.42
    shou
    -0.42
    POSITIVE LOGITS
     defaultstate
    0.88
    tagHelperRunner
    0.73
    AnchorStyles
    0.67
    /*
    0.66
     Económica
    0.65
    RTDA
    0.64
     تضيفلها
    0.62
    complexContent
    0.62
     kasarigan
    0.61
    DebuggerNonUser
    0.61
    Act Density 1.566%

    No Known Activations