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

    Neuronpedia

    INDEX
    Explanations

    significant

    np_max-act · gemini-2.0-flash

    The neuron never fires on any input—it’s effectively inactive (a “dead” neuron).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     accuses
    -0.07
    :\\
    -0.07
     Record
    -0.06
    ۲۹
    -0.06
     walk
    -0.06
     которым
    -0.06
     Tk
    -0.06
     tonnes
    -0.06
    .pnl
    -0.06
     remake
    -0.06
    POSITIVE LOGITS
     escrit
    0.07
    	dp
    0.06
     funk
    0.06
     escri
    0.06
    foregroundColor
    0.06
     Emin
    0.06
    .utilities
    0.06
    ábado
    0.06
    (dx
    0.06
     contextual
    0.06
    Act Density 0.002%

    No Known Activations