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

    Neuronpedia

    INDEX
    Explanations

    arithmetic operations and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ،
    0.53
     be
    0.50
    ال
    0.48
    ，
    0.47
     is
    0.46
    не
    0.45
     can
    0.44
     it
    0.43
    be
    0.43
    ام
    0.43
    POSITIVE LOGITS
    大脑
    0.36
    тово
    0.35
    getRedTeam
    0.35
    /
    0.35
    ла
    0.34
     }^{\
    0.33
    atation
    0.33
    деа
    0.33
    ន
    0.32
     pâte
    0.32
    Act Density 0.269%

    No Known Activations