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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Susp
    -0.07
     появи
    -0.07
     variant
    -0.06
    Suc
    -0.06
    -limit
    -0.06
    Bur
    -0.06
     plagued
    -0.06
     },
    -0.06
     Nom
    -0.06
    амп
    -0.06
    POSITIVE LOGITS
     Climate
    0.07
     singles
    0.07
    есто
    0.06
    ِي
    0.06
    vier
    0.06
    _soup
    0.06
    ainers
    0.06
     manuscript
    0.06
     poses
    0.06
    indir
    0.06
    Act Density 0.075%

    No Known Activations