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

    Neuronpedia

    INDEX
    Explanations

    connecting clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enzimas
    0.44
     área
    0.40
     propriedades
    0.39
     sebagainya
    0.39
    હુ
    0.38
     cosas
    0.38
    活动
    0.38
    都
    0.37
    知道
    0.37
    很多
    0.37
    POSITIVE LOGITS
    ad
    0.49
    in
    0.45
    ש
    0.42
    0
    0.40
    al
    0.35
    pt
    0.34
    9
    0.34
    ק
    0.34
    ים
    0.33
    it
    0.33
    Act Density 0.029%

    No Known Activations