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

    Neuronpedia

    INDEX
    Explanations

    cell

    np_max-act · gemini-2.0-flash

    The neuron activates on the token “cell” (e.g. in “cell phone,” “battery cell,” or code identifiers containing “cell”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    igth
    -0.07
     Friedrich
    -0.07
     praž
    -0.07
     Grande
    -0.07
    лишком
    -0.07
     Shapiro
    -0.07
     AGRE
    -0.06
     McGregor
    -0.06
     McGr
    -0.06
    LOUR
    -0.06
    POSITIVE LOGITS
     cell
    0.12
    cell
    0.11
    Cell
    0.11
     Cell
    0.11
    -cell
    0.09
    	cell
    0.09
     CELL
    0.09
    CELL
    0.09
    EL
    0.08
     cellular
    0.08
    Act Density 0.017%

    No Known Activations