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

    Neuronpedia

    INDEX
    Explanations

    Numbers and addition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ();↵↵↵
    -0.06
    	angle
    -0.06
    resources
    -0.06
     Für
    -0.06
    ourses
    -0.06
    ,No
    -0.06
     username
    -0.06
    stash
    -0.06
    -angle
    -0.06
    (Player
    -0.06
    POSITIVE LOGITS
     coverage
    0.07
    438
    0.06
    <br
    0.06
    oga
    0.06
     nicely
    0.06
     deduction
    0.06
    453
    0.06
     clin
    0.06
     Dice
    0.06
    -route
    0.06
    Act Density 0.001%

    No Known Activations