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

    Neuronpedia

    INDEX
    Explanations

    end

    np_max-act · gemini-2.0-flash

    The neuron fires on floating‐point numeric literals (numbers with a decimal point) in code or comments.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     matriz
    -0.07
     Girls
    -0.07
    undles
    -0.07
    Valor
    -0.06
    .getContent
    -0.06
     Раз
    -0.06
     professionals
    -0.06
     filme
    -0.06
    .places
    -0.06
    Zip
    -0.06
    POSITIVE LOGITS
    อย
    0.07
     федераль
    0.06
      
↵
    0.06
     '/';↵
    0.06
    ')
↵
    0.06
     }

↵
    0.06
     movable
    0.06
    Brush
    0.06
    "))↵
    0.06
     inventive
    0.06
    Act Density 0.010%

    No Known Activations