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

    Neuronpedia

    INDEX
    Explanations

    code comments and declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    >>>
    -1.01
     '
    -0.96
     “
    -0.96
    >
    -0.94
     ‘
    -0.88
     складу
    -0.88
     Гар
    -0.82
     había
    -0.81
    伊豆
    -0.81
     envision
    -0.81
    POSITIVE LOGITS
    ……"
    1.15
    …"
    1.12
    -//
    1.01
    ()"
    1.00
    ꦠ
    0.96
     ..."
    0.96
    !"
    0.96
    =="
    0.95
    orsing
    0.95
    amate
    0.94
    Act Density 0.085%

    No Known Activations