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

    Neuronpedia

    INDEX
    Explanations

    abbreviations and fragmented words that are not real words

    oai_token-act-pair · gemini-2.0-flash

    foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fallu
    -0.49
     <>",
    -0.43
    getMenuInflater
    -0.43
    InitVars
    -0.42
    featureID
    -0.41
     national
    -0.40
     ModelAndView
    -0.40
     nationales
    -0.38
     majo
    -0.37
     ligiloj
    -0.37
    POSITIVE LOGITS
     صوتيه
    0.70
    Rhestr
    0.69
    ract
    0.61
    atguigu
    0.61
    lying
    0.60
    leck
    0.60
    lers
    0.60
     getArguments
    0.60
    inois
    0.59
    lor
    0.59
    Act Density 6.280%

    No Known Activations