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

    Neuronpedia

    INDEX
    Explanations

    scientific papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exemplo
    -0.07
    택
    -0.06
    :p
    -0.06
    whel
    -0.06
    uku
    -0.06
    (and
    -0.06
    ひと
    -0.06
     //#
    -0.06
    =target
    -0.06
    лоп
    -0.06
    POSITIVE LOGITS
    (Application
    0.07
     dictated
    0.07
     parked
    0.06
     arttır
    0.06
     jihadists
    0.06
     FirebaseAuth
    0.06
    oğun
    0.06
     plaintiffs
    0.06
     missionaries
    0.06
     Million
    0.06
    Act Density 0.014%

    No Known Activations