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

    Neuronpedia

    INDEX
    Explanations

    models, Arena, Java, search

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     要素
    0.50
    <unused2052>
    0.48
    タグ
    0.47
     obesidad
    0.47
    シャツ
    0.46
    選択
    0.46
    檚
    0.46
     evaporates
    0.45
     ಶತ
    0.45
    dense
    0.44
    POSITIVE LOGITS
    0.49
     Google
    0.47
     আরা
    0.45
    app
    0.43
     App
    0.43
     Ava
    0.41
     https
    0.40
     Java
    0.40
     Waz
    0.40
     बाध्य
    0.40
    Act Density 0.001%

    No Known Activations