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

    Neuronpedia

    INDEX
    Explanations

    common

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     página
    -0.07
     мала
    -0.07
     synopsis
    -0.07
     última
    -0.07
    628
    -0.06
     сем
    -0.06
     rele
    -0.06
     eerste
    -0.06
    層
    -0.06
     primero
    -0.06
    POSITIVE LOGITS
     Gain
    0.07
     Deal
    0.07
    	sn
    0.06
     national
    0.06
    Trivia
    0.06
     Hash
    0.06
     روشن
    0.06
     Bank
    0.06
    ظˆ
    0.06
    κης
    0.06
    Act Density 0.001%

    No Known Activations