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

    Neuronpedia

    INDEX
    Explanations

    Horizontal lines

    np_max-act · gemini-2.0-flash

    This neuron detects document section separators, i.e. lines made up of repeated hyphens or equals signs.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Axios
    -0.07
    Constructed
    -0.07
    .samples
    -0.07
    .mm
    -0.07
     simulated
    -0.07
    _follow
    -0.07
    hat
    -0.06
    Mac
    -0.06
    $count
    -0.06
    [rand
    -0.06
    POSITIVE LOGITS
     لف
    0.06
    ení
    0.06
    (HttpContext
    0.06
     belirtilen
    0.06
     Společ
    0.06
     ListBox
    0.06
     doomed
    0.06
     carrot
    0.06
    .BASELINE
    0.06
    ома
    0.06
    Act Density 0.001%

    No Known Activations