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

    Neuronpedia

    INDEX
    Explanations

    drums

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shotgun
    -0.08
     Extensions
    -0.07
    易
    -0.07
     socialism
    -0.07
     clutter
    -0.06
     увер
    -0.06
    ров
    -0.06
    ,u
    -0.06
     bt
    -0.06
     bekannt
    -0.06
    POSITIVE LOGITS
    Uh
    0.07
    (_)
    0.06
    relude
    0.06
     Πλη
    0.06
    .require
    0.06
    aname
    0.06
    :int
    0.06
     filepath
    0.06
     RVA
    0.06
    .Failure
    0.06
    Act Density 0.035%

    No Known Activations