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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jersey
    -0.08
     wenn
    -0.07
    änder
    -0.07
    prop
    -0.07
     proceedings
    -0.07
     Member
    -0.06
    ocoder
    -0.06
    .offset
    -0.06
     Mystic
    -0.06
    Unsigned
    -0.06
    POSITIVE LOGITS
     другими
    0.07
    ，同时
    0.07
     perso
    0.06
     сем
    0.06
     профес
    0.06
     Aynı
    0.06
    /../
    0.06
     ان
    0.06
     науков
    0.06
     edilm
    0.06
    Act Density 0.006%

    No Known Activations