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

    Neuronpedia

    INDEX
    Explanations

    TF

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jar
    -0.06
     pornofilm
    -0.06
     Complete
    -0.06
     regimen
    -0.06
     Wal
    -0.06
     hlad
    -0.06
     Browns
    -0.06
    SY
    -0.06
    Buy
    -0.06
     OWN
    -0.06
    POSITIVE LOGITS
    _txn
    0.07
     superf
    0.07
    .nt
    0.07
    itness
    0.07
    荐
    0.06
    	loc
    0.06
    tolist
    0.06
    hc
    0.06
    xffff
    0.06
     Ibid
    0.06
    Act Density 0.007%

    No Known Activations