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

    Neuronpedia

    INDEX
    Explanations

    numeric values in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    citizenship, naturalization, relief

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    createNewFile
    -0.46
    必要があります
    -0.42
    CreateMap
    -0.41
    stateParams
    -0.41
     heat
    -0.41
    setState
    -0.40
     Svensson
    -0.40
    Assista
    -0.39
     nakalista
    -0.39
    msgSender
    -0.39
    POSITIVE LOGITS
    \{\\
    0.50
     Chinatown
    0.44
     Audiodateien
    0.43
     gyhoeddwyd
    0.42
    abestanden
    0.42
    }{*}{
    0.42
    ViewInit
    0.42
     Nominal
    0.41
    Nominal
    0.41
    expandindo
    0.41
    Act Density 0.017%

    No Known Activations