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

    Neuronpedia

    INDEX
    Explanations

    percept

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Civ
    -0.06
    Dest
    -0.06
     Cocktail
    -0.06
     Willow
    -0.06
    램
    -0.06
    ках
    -0.06
    	bytes
    -0.06
     poetry
    -0.06
    osos
    -0.06
    .rc
    -0.06
    POSITIVE LOGITS
     pracov
    0.06
    .getValueAt
    0.06
    acula
    0.06
    #\
    0.06
     Sabb
    0.06
    @
    0.06
     Monk
    0.06
    Recognizer
    0.06
    	Game
    0.06
    Telefone
    0.06
    Act Density 0.002%

    No Known Activations