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

    Neuronpedia

    INDEX
    Explanations

    Research papers

    np_max-act · gemini-2.0-flash

    This neuron fires on formal scientific or academic terminology and section-introduction words characteristic of technical writing.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _np
    -0.07
    _vm
    -0.06
     Bergen
    -0.06
     Bulgarian
    -0.06
    М
    -0.06
     Київ
    -0.06
    iena
    -0.06
     Deep
    -0.06
    Frames
    -0.06
    YLE
    -0.06
    POSITIVE LOGITS
    átek
    0.07
    /|
    0.06
    ‚ط
    0.06
    _TEX
    0.06
     salv
    0.06
    lement
    0.06
     واس
    0.06
     Συ
    0.06
     MacOS
    0.06
    ActiveSheet
    0.06
    Act Density 0.065%

    No Known Activations