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

    Neuronpedia

    INDEX
    Explanations

    years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    涿
    0.50
    韪
    0.47
    𒁹
    0.46
    ากาศ
    0.44
     سہ
    0.44
     sAlarm
    0.44
     conteúdos
    0.43
    绛
    0.43
     দীন
    0.43
    𒁾
    0.43
    POSITIVE LOGITS
    -
    0.54
     (
    0.53
    {
    0.52
    <sup>
    0.49
    r
    0.49
    ce
    0.49
    X
    0.49
     {
    0.49
    ier
    0.47
     X
    0.47
    Act Density 0.002%

    No Known Activations