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

    Neuronpedia

    INDEX
    Explanations

    Software licenses

    np_max-act · gemini-2.0-flash

    The neuron fires on floating‐point numeric literals (numbers containing a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     замен
    -0.07
     generic
    -0.07
    (`<
    -0.06
     days
    -0.06
     Gui
    -0.06
    
    -0.06
     Gardner
    -0.06
     prepare
    -0.06
     Contin
    -0.06
    (depend
    -0.06
    POSITIVE LOGITS
    ælland
    0.07
    �
    0.06
    ेण
    0.06
    LocalizedMessage
    0.06
     heavyweight
    0.06
    yet
    0.06
     disappearing
    0.06
     staple
    0.06
    NECT
    0.06
    roat
    0.06
    Act Density 0.007%

    No Known Activations