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

    Neuronpedia

    INDEX
    Explanations

    ones

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    第八
    -0.09
    <?↵
    -0.08
    WebService
    -0.08
     realloc
    -0.07
    .git
    -0.07
    哇
    -0.07
     FIX
    -0.07
     Feast
    -0.07
     exploring
    -0.07
     asynchronous
    -0.07
    POSITIVE LOGITS
     ones
    0.09
    ками
    0.08
    〳
    0.07
    ned
    0.07
     plywood
    0.07
     들
    0.07
    _Input
    0.07
    Entries
    0.07
    ے
    0.07
     entity
    0.07
    Act Density 0.010%

    No Known Activations