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

    Neuronpedia

    INDEX
    Explanations

    energy

    np_max-act · gemini-2.0-flash

    characters and symbols that represent mathematical equations or expressions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     NBA
    -0.07
    	text
    -0.06
    WK
    -0.06
    UTTON
    -0.06
    StdString
    -0.06
    vere
    -0.06
    estroy
    -0.06
    %↵
    -0.06
     tuyệt
    -0.06
    Typography
    -0.06
    POSITIVE LOGITS
    .e
    0.07
    인이
    0.06
     О
    0.06
     Keeper
    0.06
     kW
    0.06
    //
    0.06
    ري
    0.06
    _WS
    0.06
     Hamas
    0.06
    .Created
    0.06
    Act Density 0.006%

    No Known Activations