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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    This neuron detects floating-point numeric tokens (decimal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _PIPELINE
    -0.07
    sprintf
    -0.07
    ocations
    -0.07
     Fold
    -0.06
     recognizes
    -0.06
     rendered
    -0.06
     mang
    -0.06
    pcodes
    -0.06
    ArrayOf
    -0.06
    	cfg
    -0.06
    POSITIVE LOGITS
     ALSO
    0.07
     hvor
    0.07
     dois
    0.06
    ум
    0.06
    focus
    0.06
    IGHT
    0.06
     flashy
    0.06
     imu
    0.06
    aoke
    0.06
     initialState
    0.06
    Act Density 0.039%

    No Known Activations