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

    Neuronpedia

    INDEX
    Explanations

    Searching, questions, code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tras
    -0.32
    ä¸Ģåı£
    -0.28
    leaders
    -0.27
    txt
    -0.26
    füg
    -0.26
    tx
    -0.26
    vert
    -0.25
    TX
    -0.25
    hari
    -0.24
    æĭŁ
    -0.24
    POSITIVE LOGITS
     followed
    0.28
     werk
    0.27
     supplemented
    0.26
    åıªè§ģ
    0.26
    女æĢ§æľĭåıĭ
    0.26
     :</
    0.26
    _where
    0.25
    Where
    0.25
     Brut
    0.24
     rooted
    0.24
    Act Density 0.057%

    No Known Activations