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

    Neuronpedia

    INDEX
    Explanations

    function arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Shakespeare
    0.71
    และความ
    0.64
    Economics
    0.57
    \}=
    0.57
     Turner
    0.56
    Science
    0.56
    Theorem
    0.55
    Opera
    0.55
    Type
    0.55
    Turner
    0.55
    POSITIVE LOGITS
     params
    1.03
     аргу
    1.01
     argumentos
    0.98
     arguments
    0.96
     parameters
    0.94
    params
    0.89
    parameters
    0.89
     paramètres
    0.89
     parâmetros
    0.88
     args
    0.88
    Act Density 0.004%

    No Known Activations