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

    Neuronpedia

    INDEX
    Explanations

    cloud and associated services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    籥
    -2.14
     使っ
    -2.11
     harsh
    -1.93
    </strong>
    -1.88
    旸
    -1.85
    錚
    -1.85
    Ɑ
    -1.77
     especially
    -1.76
    ⸪
    -1.76
    歘
    -1.73
    POSITIVE LOGITS
    ଃ
    2.25
    $
    2.02
    th
    1.91
    {
    1.90
    .
    1.81
     Это
    1.81
     This
    1.81
     Thats
    1.80
    These
    1.80
    ri
    1.80
    Act Density 0.005%

    No Known Activations