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

    Neuronpedia

    INDEX
    Explanations

    _crossentropy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _bad
    -0.06
     zg
    -0.06
     mở
    -0.06
    _endpoint
    -0.06
     painters
    -0.06
    ą
    -0.06
     lá
    -0.06
     []↵↵↵
    -0.06
    ają
    -0.06
     عص
    -0.05
    POSITIVE LOGITS
     비
    0.09
     Arch
    0.07
    インタ
    0.07
     ARC
    0.07
    part
    0.07
     Mitchell
    0.07
     예
    0.06
     SCI
    0.06
    ar
    0.06
     Dave
    0.06
    Act Density 0.001%

    No Known Activations