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

    Neuronpedia

    INDEX
    Explanations

    matrix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Certainly
    -0.08
     If
    -0.07
    Da
    -0.07
     medio
    -0.07
    Africa
    -0.07
     if
    -0.07
    After
    -0.07
     porad
    -0.06
    obraz
    -0.06
     ninety
    -0.06
    POSITIVE LOGITS
    ython
    0.07
    ность
    0.06
    _FORWARD
    0.06
     Inject
    0.06
    -hook
    0.06
    istical
    0.06
    _trans
    0.06
    .vocab
    0.06
    eced
    0.06
    ="[
    0.06
    Act Density 0.160%

    No Known Activations