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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric result tokens in the output—specifically on the floating‐point answer values (decimal fractions) of the derivative calculations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    OGLE
    -0.07
     Visualization
    -0.06
    /delete
    -0.06
     nozzle
    -0.06
    .INVISIBLE
    -0.06
     wm
    -0.06
     інш
    -0.06
    .arm
    -0.06
    -)
    -0.06
    :result
    -0.06
    POSITIVE LOGITS
    ám
    0.07
     ALERT
    0.07
     penalties
    0.07
     Penalty
    0.07
     };
↵
    0.06
     ها
    0.06
    .
↵
    0.06
    Receive
    0.06
    ها
    0.06
    주세요
    0.06
    Act Density 0.001%

    No Known Activations