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

    Neuronpedia

    INDEX
    Explanations

    personal anecdotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cly
    -0.07
     stare
    -0.06
    creen
    -0.06
     museum
    -0.06
     있을
    -0.06
     Oh
    -0.06
     climate
    -0.06
     infamous
    -0.06
     MySql
    -0.06
     Herald
    -0.06
    POSITIVE LOGITS
    arsimp
    0.07
    realDonaldTrump
    0.07
    การต
    0.06
     πριν
    0.06
    Exclude
    0.06
    ='".$_
    0.06
    -param
    0.06
    組織
    0.06
     theano
    0.06
    -setup
    0.06
    Act Density 0.055%

    No Known Activations