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

    Neuronpedia

    INDEX
    Explanations

    designing assessment or NAME plans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    음
    0.72
    一家
    0.71
    メイド
    0.65
    ाह
    0.65
    鸹
    0.65
     avantage
    0.64
    特征
    0.64
    说道
    0.63
     scoperto
    0.62
    க்
    0.61
    POSITIVE LOGITS
    жды
    1.05
     hibiscus
    0.86
     एमटीएस
    0.86
    ು
    0.86
     timelapse
    0.85
     magní
    0.85
     Botox
    0.84
     kawaii
    0.84
     jacuzzi
    0.82
     autoc
    0.82
    Act Density 0.000%

    No Known Activations