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

    Neuronpedia

    INDEX
    Explanations

    begin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Luck
    -0.07
     traff
    -0.07
    Scott
    -0.07
     Scott
    -0.07
     ItemType
    -0.07
    ト
    -0.06
     ateş
    -0.06
     mistr
    -0.06
    瑞
    -0.06
     extortion
    -0.06
    POSITIVE LOGITS
     begin
    0.16
     began
    0.15
     begins
    0.14
     begun
    0.13
     beginning
    0.12
    	begin
    0.11
     Beginning
    0.11
     Begin
    0.10
    Beginning
    0.10
    Begin
    0.10
    Act Density 0.038%

    No Known Activations