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

    Neuronpedia

    INDEX
    Explanations

    Null or false values

    np_max-act · gemini-2.0-flash

    This neuron never activates—it does not respond to any tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ак
    -0.07
    (lines
    -0.07
     endanger
    -0.07
    Instr
    -0.07
     ق
    -0.06
    .pb
    -0.06
     Charter
    -0.06
     bs
    -0.06
     Giải
    -0.06
     amino
    -0.06
    POSITIVE LOGITS
    umor
    0.07
    :set
    0.07
    ,[],
    0.07
     antibiot
    0.07
    urgy
    0.06
     Vegas
    0.06
    IDTH
    0.06
    atti
    0.06
    nám
    0.06
    JT
    0.06
    Act Density 0.018%

    No Known Activations