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

    Neuronpedia

    INDEX
    Explanations

    Math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     america
    -0.09
    传真
    -0.08
     anonymously
    -0.08
    -email
    -0.08
     birthdays
    -0.08
     spreadsheets
    -0.08
     Rico
    -0.08
     brainstorm
    -0.08
    六合彩
    -0.08
    ASCII
    -0.08
    POSITIVE LOGITS
    cond
    0.08
    (Camera
    0.08
    (mesh
    0.08
     dominance
    0.08
    (Border
    0.07
    _RELEASE
    0.07
    (Equal
    0.07
     unjust
    0.07
    (cond
    0.07
    (Rect
    0.07
    Act Density 0.029%

    No Known Activations