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

    Neuronpedia

    INDEX
    Explanations

    phrases that suggest conditionality

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.93
    webElementXpaths
    -0.80
     beginnetje
    -0.79
    RLock
    -0.65
    SharedDtor
    -0.65
    تقاوى
    -0.64
    sizeCache
    -0.64
     Numerade
    -0.64
     ***!
    -0.64
    WebVitals
    -0.63
    POSITIVE LOGITS
    quehanna
    0.54
    eaus
    0.47
     Footh
    0.47
    jsh
    0.45
    
    0.45
    ینک
    0.44
    moreland
    0.43
     Untitled
    0.42
    ULDER
    0.42
     Faso
    0.42
    Act Density 0.189%

    No Known Activations