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

    Neuronpedia

    INDEX
    Explanations

    dishware

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Campus
    -0.08
    poi
    -0.08
    ko
    -0.08
     ontdekken
    -0.07
    Jaw
    -0.07
     described
    -0.07
     Exhib
    -0.07
    aden
    -0.07
     Cities
    -0.07
    راسة
    -0.07
    POSITIVE LOGITS
     fundos
    0.08
     bekl
    0.08
     оформления
    0.08
     оформ
    0.08
    )(↵
    0.08
    รอง
    0.08
     Sanchez
    0.08
     liners
    0.08
    (stmt
    0.08
     individuelles
    0.07
    Act Density 0.004%

    No Known Activations