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

    Neuronpedia

    INDEX
    Explanations

    Citations

    np_max-act · gemini-2.0-flash

    This neuron does not respond to any tokens—it remains inactive and does not detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Object
    -0.07
    Restr
    -0.07
     COLUMN
    -0.07
     defaulted
    -0.07
     ReadOnly
    -0.06
    „V
    -0.06
     breakfast
    -0.06
    Path
    -0.06
    fr
    -0.06
    Objects
    -0.06
    POSITIVE LOGITS
    Featured
    0.07
     حکم
    0.06
    真是
    0.06
     provozu
    0.06
    emd
    0.06
     JDK
    0.06
     šest
    0.06
    oint
    0.06
     Featured
    0.06
     жар
    0.05
    Act Density 0.008%

    No Known Activations