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

    Neuronpedia

    INDEX
    Explanations

    code or markup tags

    np_max-act · gemini-2.0-flash

    This neuron is inactive (a “dead” neuron) and does not respond to any tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     insure
    -0.07
    wagon
    -0.07
    globals
    -0.06
     мус
    -0.06
     silence
    -0.06
     clearfix
    -0.06
     mesa
    -0.06
    usan
    -0.06
     Israel
    -0.06
    bars
    -0.06
    POSITIVE LOGITS
     transient
    0.07
    反应
    0.07
    Impl
    0.06
    .basic
    0.06
    ,$
    0.06
     consequence
    0.06
    otten
    0.06
    록
    0.06
     Exceptions
    0.06
    cce
    0.06
    Act Density 0.031%

    No Known Activations