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

    Neuronpedia

    INDEX
    Explanations

    reviews and ratings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shoulders
    -0.07
    .tsv
    -0.06
    umbles
    -0.06
     trench
    -0.06
    -safe
    -0.06
    fung
    -0.06
     Smy
    -0.06
    Av
    -0.06
     receipt
    -0.05
    tuk
    -0.05
    POSITIVE LOGITS
     dood
    0.07
    Discuss
    0.07
    út
    0.07
       
    0.07
     meisje
    0.07
    liğine
    0.06
     september
    0.06
    nímu
    0.06
     Moral
    0.06
    ’l
    0.06
    Act Density 0.024%

    No Known Activations