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

    Neuronpedia

    INDEX
    Explanations

    Seeing

    np_max-act · gemini-2.0-flash

    This neuron responds to comma tokens, marking clause‐separating punctuation.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     kings
    -0.07
     Pretty
    -0.07
     quien
    -0.07
     significant
    -0.06
     Project
    -0.06
    	strcat
    -0.06
     самый
    -0.06
     teased
    -0.06
    PO
    -0.06
     proprietary
    -0.06
    POSITIVE LOGITS
     prez
    0.07
     муль
    0.06
    .Pre
    0.06
     sare
    0.06
     pitching
    0.06
     Resize
    0.06
    _reset
    0.06
    setIcon
    0.06
    /terms
    0.06
    Recovered
    0.06
    Act Density 0.007%

    No Known Activations