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

    Neuronpedia

    INDEX
    Explanations

    [[

    np_max-act · gemini-2.0-flash

    This neuron activates on floating‐point numeric literals (i.e. tokens containing decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    UNICATION
    -0.07
    ΟΣ
    -0.07
     Beast
    -0.07
    िक
    -0.06
    CESS
    -0.06
     Chemistry
    -0.06
     不
    -0.06
     desert
    -0.06
     FileOutputStream
    -0.06
     Dor
    -0.06
    POSITIVE LOGITS
     [[
    0.07
     ]}↵
    0.06
    .QLabel
    0.06
     embody
    0.06
    |}↵
    0.06
     />'
    0.06
     ’
    0.06
    /md
    0.06
     《
    0.06
    _bits
    0.06
    Act Density 0.001%

    No Known Activations