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
     [
    0.57
    []
    0.55
     []
    0.53
    [])
    0.51
     Argument
    0.50
     argument
    0.49
    argument
    0.47
    [],
    0.45
    Argument
    0.44
     [,
    0.43
    POSITIVE LOGITS
     args
    0.54
     "--
    0.54
     Eqs
    0.50
    args
    0.47
    ।--
    0.46
    }--
    0.44
    ("--
    0.44
     `--
    0.43
     gols
    0.42
     "&
    0.42
    Act Density 0.005%

    No Known Activations