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

    Neuronpedia

    INDEX
    Explanations

    company ownership

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ComponentName
    0.46
    schl
    0.40
     qualified
    0.37
     setName
    0.36
     SCIENCE
    0.36
    ronomie
    0.36
    芍
    0.35
    wissenschaft
    0.35
     名称
    0.35
     Qualified
    0.35
    POSITIVE LOGITS
     Lesser
    0.44
     संस्कारों
    0.43
     szé
    0.40
     Great
    0.39
    Great
    0.39
    ธุรก
    0.39
     खांसी
    0.39
     AFI
    0.38
    ரீ
    0.38
     posed
    0.37
    Act Density 0.001%

    No Known Activations