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

    Neuronpedia

    INDEX
    Explanations

    margin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .CV
    -0.07
    lhs
    -0.07
     этих
    -0.06
     centroids
    -0.06
    葉
    -0.06
     فناوری
    -0.06
     byte
    -0.06
    به
    -0.06
    EqualTo
    -0.06
    {lng
    -0.06
    POSITIVE LOGITS
    осуд
    0.07
     Quiet
    0.07
    Sac
    0.07
    _DEAD
    0.07
    rn
    0.06
    addr
    0.06
    zn
    0.06
    coles
    0.06
    rian
    0.06
    γα
    0.06
    Act Density 0.005%

    No Known Activations