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

    Neuronpedia

    INDEX
    Explanations

    Zero

    np_max-act · gemini-2.0-flash

    This neuron never activates on any token in these snippets—it appears to be effectively “dead” and isn’t detecting any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	file
    -0.06
     وجود
    -0.06
     collaps
    -0.06
    Dest
    -0.06
     oste
    -0.06
     argent
    -0.06
     Ep
    -0.06
     свид
    -0.06
     ADDR
    -0.06
    ози
    -0.06
    POSITIVE LOGITS
    ICO
    0.07
     "-"
    0.06
    ="./
    0.06
    ],[-
    0.06
    _>
    0.06
    สนาม
    0.06
    ...
    0.06
    normalize
    0.06
     ("-
    0.06
     correlated
    0.06
    Act Density 0.004%

    No Known Activations