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

    Neuronpedia

    INDEX
    Explanations

    descriptive word followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     этом
    0.41
     cosidd
    0.34
     інші
    0.33
     மற்றொரு
    0.33
     사용
    0.31
    というと
    0.31
     detta
    0.30
    Kaynak
    0.30
     Hinweis
    0.30
     آمریکا
    0.30
    POSITIVE LOGITS
    -
    0.42
    7
    0.40
    ing
    0.36
    ارع
    0.34
    рана
    0.32
     (!)
    0.32
     rada
    0.32
    ologically
    0.31
    ratulations
    0.31
    ”、“
    0.31
    Act Density 0.076%

    No Known Activations