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

    Neuronpedia

    INDEX
    Explanations

    start typing, suggest ideas, built into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    äck
    0.38
    MatContext
    0.35
     þing
    0.34
     nonfiction
    0.34
     ṣ
    0.34
     solidification
    0.34
     inactivació
    0.34
     unquestionably
    0.34
    hältnisse
    0.34
     verità
    0.33
    POSITIVE LOGITS
    and
    0.44
    i
    0.42
    2
    0.40
    /
    0.40
    7
    0.39
    3
    0.37
    颖
    0.36
    しやすい
    0.36
    9
    0.36
     and
    0.35
    Act Density 0.155%

    No Known Activations