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

    Neuronpedia

    INDEX
    Explanations

    help

    np_max-act · gemini-2.0-flash

    The neuron activates on causal/explanatory phrasing—especially the “help to …​” construction that introduces a function or purpose.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Daily
    -0.07
    hendis
    -0.06
    manda
    -0.06
    shows
    -0.06
    _Widget
    -0.06
    venient
    -0.06
     saldırı
    -0.05
    woord
    -0.05
    (dict
    -0.05
    avors
    -0.05
    POSITIVE LOGITS
     VAR
    0.08
     cyc
    0.07
    _strcmp
    0.07
     extern
    0.07
     Templ
    0.07
    .ImageIcon
    0.07
    >About
    0.07
    *\
    0.07
    /math
    0.07
    _SYSTEM
    0.07
    Act Density 0.037%

    No Known Activations