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

    Neuronpedia

    INDEX
    Explanations

    error

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    алу
    -0.07
    tical
    -0.06
    ану
    -0.06
    _DATA
    -0.06
    rb
    -0.06
    ét
    -0.06
     Dominic
    -0.06
    ника
    -0.06
    wh
    -0.06
     management
    -0.06
    POSITIVE LOGITS
    /react
    0.07
    彩
    0.07
    -between
    0.07
    zano
    0.07
    Iter
    0.06
    _EC
    0.06
     pt
    0.06
     swingerclub
    0.06
     제가
    0.06
    ?[
    0.06
    Act Density 0.029%

    No Known Activations