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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	address
    -0.07
     testimony
    -0.07
     affinity
    -0.07
     طور
    -0.07
     cure
    -0.07
    顔
    -0.07
    imore
    -0.06
     cabeza
    -0.06
     CRE
    -0.06
     Thousand
    -0.06
    POSITIVE LOGITS
    types
    0.07
     )->
    0.07
     потрібно
    0.07
    ẻ
    0.07
    ([&
    0.07
     futures
    0.06
    Int
    0.06
    인을
    0.06
    .getLongitude
    0.06
    Cannot
    0.06
    Act Density 0.623%

    No Known Activations