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

    Neuronpedia

    INDEX
    Explanations

    edit

    np_max-act · gemini-2.0-flash

    This neuron fires on mentions of “edit” or “editing” (e.g. inline row‐editing state) in code or discussion of editing operations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _uv
    -0.07
    jom
    -0.07
     vm
    -0.07
     KS
    -0.06
     SA
    -0.06
     intest
    -0.06
     JT
    -0.06
     stringify
    -0.06
    htm
    -0.06
     toast
    -0.06
    POSITIVE LOGITS
     přisp
    0.07
    식
    0.07
    road
    0.07
    larda
    0.06
    elfth
    0.06
     PLATFORM
    0.06
    willReturn
    0.06
    ida
    0.06
    ulatory
    0.06
     Wayback
    0.06
    Act Density 0.002%

    No Known Activations