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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     („
    1.32
     (“
    1.28
     ("
    1.24
     “‘
    1.20
    “
    1.16
     “
    1.12
    “(
    1.10
     ”
    1.09
     `"
    1.09
    ʺ
    1.09
    POSITIVE LOGITS
    -
    1.84
    :
    1.05
    '
    0.96
    {
    0.84
    ,
    0.83
    -}\
    0.80
    이션
    0.79
    [],
    0.78
    (
    0.78
    ],
    0.78
    Act Density 0.000%

    No Known Activations