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

    Neuronpedia

    INDEX
    Explanations

    dereferencing pointer `*`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vorm
    1.20
    ać
    1.19
    ara
    1.16
    тся
    1.16
    א
    1.11
    ن
    1.09
    Reactor
    1.03
    á
    1.00
    uu
    0.98
    ت
    0.98
    POSITIVE LOGITS
    নিবার
    0.96
    ূল্যে
    0.94
     appla
    0.91
     prisoners
    0.87
     handcuffed
    0.87
    З
    0.86
     merhabalar
    0.86
    spruch
    0.85
     Frankel
    0.84
    𝘳
    0.84
    Act Density 0.007%

    No Known Activations