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

    Neuronpedia

    INDEX
    Explanations

    URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Extra
    -0.07
     Skills
    -0.07
     더
    -0.06
     Capt
    -0.06
     那
    -0.06
    Drug
    -0.06
     Hep
    -0.06
    “One
    -0.06
     JJ
    -0.06
     zeal
    -0.06
    POSITIVE LOGITS
    .bit
    0.07
    dığında
    0.06
     Finn
    0.06
     paramString
    0.06
    WebKit
    0.06
     současné
    0.06
    ,//
    0.06
    دار
    0.06
    crets
    0.06
    terraform
    0.06
    Act Density 0.006%

    No Known Activations