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

    Neuronpedia

    INDEX
    Explanations

    feature selection, engineering, extraction, stores

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     delici
    0.45
     Vivi
    0.43
    ミ
    0.40
    มิ
    0.40
     việc
    0.40
     vaja
    0.40
    نا
    0.39
     Biscuit
    0.39
     EXE
    0.39
    ﾛ
    0.39
    POSITIVE LOGITS
     특징
    1.11
    特征
    1.09
     features
    1.09
    特性
    1.05
    features
    1.03
    特徴
    1.02
     características
    1.02
     characteristics
    0.98
     Features
    0.98
     feature
    0.98
    Act Density 0.023%

    No Known Activations