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

    Neuronpedia

    INDEX
    Explanations

    match

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Exposure
    -0.07
     fac
    -0.07
     uvád
    -0.06
     waste
    -0.06
    stitutions
    -0.06
    lycer
    -0.06
     Bars
    -0.06
    782
    -0.06
    Most
    -0.06
     Soul
    -0.06
    POSITIVE LOGITS
     match
    0.07
    battle
    0.07
     Raider
    0.07
     fight
    0.07
     bouts
    0.06
     battle
    0.06
     commem
    0.06
    atomic
    0.06
     gig
    0.06
    _mC
    0.06
    Act Density 0.027%

    No Known Activations