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

    Neuronpedia

    INDEX
    Explanations

    derivatives

    np_max-act · gemini-2.0-flash

    The neuron detects exponentiation and power‐notation tokens (e.g. “**”) in mathematical expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Link
    -0.07
     subsequently
    -0.07
    Redirect
    -0.07
     shade
    -0.06
     stunt
    -0.06
    iou
    -0.06
    =result
    -0.06
     Preservation
    -0.06
    _HOST
    -0.06
    Hop
    -0.06
    POSITIVE LOGITS
    +'&
    0.07
    encers
    0.07
    렇
    0.07
     béné
    0.06
     unserer
    0.06
     можлив
    0.06
    */↵↵
    0.06
     stě
    0.06
    olvable
    0.06
     музы
    0.06
    Act Density 0.009%

    No Known Activations