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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stuff
    -0.07
    oine
    -0.07
    -android
    -0.07
    ܤ
    -0.07
    荀
    -0.07
    头脑
    -0.07
    xffff
    -0.07
    🐕
    -0.07
    Ḳ
    -0.07
    armac
    -0.07
    POSITIVE LOGITS
     guit
    0.07
    "How
    0.07
    כיכר
    0.07
     decision
    0.07
     library
    0.07
     UW
    0.06
    irus
    0.06
     Common
    0.06
     далеко
    0.06
     parties
    0.06
    Act Density 0.000%

    No Known Activations