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

    Neuronpedia

    INDEX
    Explanations

    math expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gently
    -0.06
    桑
    -0.06
    ислов
    -0.06
    Tac
    -0.06
     AUTH
    -0.06
     желуд
    -0.06
    keley
    -0.06
    ervers
    -0.06
    자는
    -0.06
     існу
    -0.06
    POSITIVE LOGITS
    '})
    0.06
     obsessive
    0.06
    IDI
    0.06
    	vector
    0.06
    []}
    0.06
     poetry
    0.06
    �
    0.06
    '%(
    0.06
    567
    0.06
    []>(
    0.06
    Act Density 0.003%

    No Known Activations