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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash

    Explanation of neuron 4 behavior: the main thing this neuron does is find colon characters (:) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .weapon
    -0.07
     submar
    -0.07
    .plugins
    -0.06
     일이
    -0.06
     batch
    -0.06
     savings
    -0.06
    =read
    -0.06
    (file
    -0.06
    [block
    -0.06
    _DECREF
    -0.06
    POSITIVE LOGITS
    ENUM
    0.07
     sch
    0.06
     Barbie
    0.06
     ischem
    0.06
    _ATTRIB
    0.06
    esign
    0.06
    <Renderer
    0.06
     ballo
    0.06
    aab
    0.06
    /terms
    0.06
    Act Density 0.020%

    No Known Activations