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

    Neuronpedia

    INDEX
    Explanations

    type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	vertex
    -0.08
     جنوب
    -0.08
     hare
    -0.07
    .central
    -0.07
    販
    -0.07
    .SuspendLayout
    -0.07
     متخصص
    -0.07
    /open
    -0.07
    یده
    -0.06
    /menu
    -0.06
    POSITIVE LOGITS
    dT
    0.07
     outright
    0.06
    started
    0.06
    subtype
    0.06
    -cigaret
    0.06
    uela
    0.06
    ],[
    0.06
    statement
    0.06
     vä
    0.06
    战争
    0.06
    Act Density 0.001%

    No Known Activations