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

    Neuronpedia

    INDEX
    Explanations

    Code related to UI actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +
    -0.08
     offensive
    -0.07
    Confidence
    -0.07
    .Status
    -0.07
    -0.07
     ag
    -0.07
    ircular
    -0.07
     ?>/
    -0.06
     agony
    -0.06
     melee
    -0.06
    POSITIVE LOGITS
     Zwischen
    0.09
     таму
    0.09
     briefing
    0.09
    ამდე
    0.09
     descans
    0.09
     době
    0.09
     silloin
    0.09
     dêr
    0.09
     tijdens
    0.08
    анее
    0.08
    Act Density 0.000%
    No Known Activations