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

    Neuronpedia

    INDEX
    Explanations

    pages in URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gamme
    0.42
     miniatures
    0.42
    ้วน
    0.41
     კიდ
    0.40
     begren
    0.39
    URNIZOR
    0.39
     wymaga
    0.39
     број
    0.39
     näher
    0.39
     schwier
    0.38
    POSITIVE LOGITS
    cu
    0.41
     செயல்ப
    0.40
    carry
    0.38
    Thread
    0.37
    svelte
    0.37
    Ü
    0.37
     taşı
    0.36
    ísmo
    0.36
    ality
    0.36
    扯
    0.36
    Act Density 0.004%

    No Known Activations