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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron activates on floating-point numeric literals (numbers containing a decimal point) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     pressures
    -0.07
    _var
    -0.06
     national
    -0.06
    .likes
    -0.06
     nationwide
    -0.06
    utation
    -0.06
    -element
    -0.06
     Nichols
    -0.06
     Tem
    -0.06
     once
    -0.06
    POSITIVE LOGITS
     бок
    0.06
    ٩
    0.06
    /gpio
    0.06
     Midi
    0.06
     przypad
    0.06
    }}},↵
    0.06
     โ
    0.06
     cung
    0.06
     und
    0.06
    @Repository
    0.06
    Act Density 0.266%

    No Known Activations