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

    Neuronpedia

    INDEX
    Explanations

    movies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    restrial
    -0.07
     quân
    -0.07
     Sultan
    -0.07
    מרחב
    -0.07
     qualité
    -0.07
    .mods
    -0.06
    艅
    -0.06
    liest
    -0.06
     Spielberg
    -0.06
    纂
    -0.06
    POSITIVE LOGITS
    ucid
    0.07
     Vital
    0.07
     recur
    0.07
     DIR
    0.07
     anders
    0.06
    𝐗
    0.06
    YZ
    0.06
     arise
    0.06
    ---↵
    0.06
     refused
    0.06
    Act Density 0.060%

    No Known Activations