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

    Neuronpedia

    INDEX
    Explanations

    non

    np_max-act · gemini-2.0-flash

    The neuron never activates on any tokens—it doesn’t detect or respond to any specific text patterns.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ctal
    -0.07
     albums
    -0.07
    今年
    -0.07
     Samp
    -0.07
    .Dep
    -0.06
     Shel
    -0.06
    comed
    -0.06
    dup
    -0.06
     польз
    -0.06
    .bel
    -0.06
    POSITIVE LOGITS
     designated
    0.06
    ouri
    0.06
     non
    0.06
     block
    0.06
     revolution
    0.06
    .onreadystatechange
    0.06
    αρά
    0.06
    /lists
    0.06
    HttpRequest
    0.06
    **
↵
    0.06
    Act Density 0.027%

    No Known Activations