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

    Neuronpedia

    INDEX
    Explanations

    Steps in a process

    np_max-act · gemini-2.0-flash

    This neuron does not activate on any of the shown tokens—it remains effectively inactive and does not detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     dit
    -0.06
     输出
    -0.06
     ruthless
    -0.06
     mun
    -0.06
     starving
    -0.06
    Це
    -0.06
    ":
↵
    -0.06
    ひと
    -0.06
     navigator
    -0.06
    themes
    -0.06
    POSITIVE LOGITS
    Initial
    0.06
     Vernon
    0.06
    /file
    0.06
    _atom
    0.06
    NSE
    0.06
    authorize
    0.06
    Connector
    0.06
    (pair
    0.06
    slider
    0.06
    threat
    0.06
    Act Density 0.003%

    No Known Activations