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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rac
    -0.06
    Solo
    -0.06
     irm
    -0.06
     sightings
    -0.06
    碎
    -0.06
     judgment
    -0.06
    anden
    -0.06
    OGLE
    -0.06
     carrying
    -0.06
     mandates
    -0.06
    POSITIVE LOGITS
     congratulations
    0.06
     OSP
    0.06
     detainees
    0.06
    _FS
    0.06
    ')}}↵
    0.06
     Hodg
    0.06
    ())));↵
    0.06
    ео
    0.06
     Axes
    0.06
    ्ग
    0.06
    Act Density 0.060%

    No Known Activations