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

    Neuronpedia

    INDEX
    Explanations

    location and coordinates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    j
    0.50
    ב
    0.46
    ല്‍
    0.46
    然
    0.45
    能
    0.45
    Als
    0.45
    ലെ
    0.45
     जरिए
    0.44
    苣
    0.44
    reveal
    0.43
    POSITIVE LOGITS
    𝑃
    0.55
     begrenzt
    0.50
    獄
    0.48
     ents
    0.47
    缀
    0.47
     behold
    0.47
    ranger
    0.46
    ]])
    0.46
     intersects
    0.45
    OVERRIDES
    0.45
    Act Density 0.227%

    No Known Activations