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

    Neuronpedia

    INDEX
    Explanations

    technological development and innovation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     on
    1.26
    u
    1.14
     as
    1.07
    ed
    0.95
    1
    0.93
    on
    0.92
    ,
    0.88
    0
    0.86
    r
    0.85
    ED
    0.84
    POSITIVE LOGITS
    <0x85>
    0.92
    0.90
    '
    0.86
    <0x89>
    0.82
    (
    0.82
    ’
    0.80
    <0xB2>
    0.79
    <0xB1>
    0.76
    <0x86>
    0.73
    {
    0.73
    Act Density 0.020%

    No Known Activations