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

    Neuronpedia

    INDEX
    Explanations

    furniture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Token
    -0.07
    옙
    -0.07
    (Y
    -0.07
     Participants
    -0.07
    .moveToNext
    -0.07
     Locked
    -0.07
    Drivers
    -0.07
    (v
    -0.07
    .AR
    -0.06
    ForgeryToken
    -0.06
    POSITIVE LOGITS
    救命
    0.07
     hn
    0.07
     Sab
    0.07
    赞誉
    0.07
    نزل
    0.07
     שר
    0.06
    ATERIAL
    0.06
    '])↵↵↵
    0.06
    fbe
    0.06
    各行各业
    0.06
    Act Density 0.074%

    No Known Activations