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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    كرة
    -0.07
     GUILayout
    -0.06
    Cold
    -0.06
    ≡
    -0.06
     exposures
    -0.06
     having
    -0.06
    |RF
    -0.06
     efter
    -0.06
    喝
    -0.06
     погляд
    -0.06
    POSITIVE LOGITS
    _tools
    0.07
    _puts
    0.07
     Block
    0.06
     SCI
    0.06
    献
    0.06
    _bw
    0.06
    (socket
    0.06
    ulous
    0.06
     operand
    0.06
     northwest
    0.06
    Act Density 0.166%

    No Known Activations