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

    Neuronpedia

    INDEX
    Explanations

    especially

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ॉर्म
    0.42
     vidéo
    0.42
     ভিস
    0.39
     ボタン
    0.38
    ޮ
    0.38
     अनुश
    0.37
     केटी
    0.37
    视频
    0.37
     WEBSITE
    0.37
    स्फोट
    0.36
    POSITIVE LOGITS
    Additive
    0.37
     тера
    0.37
    roductive
    0.37
     Solubility
    0.36
     pathogenesis
    0.35
     وار
    0.35
     держави
    0.34
     знали
    0.34
    committees
    0.34
     Respublik
    0.34
    Act Density 0.008%

    No Known Activations