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

    Neuronpedia

    INDEX
    Explanations

    angle problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     poésie
    -0.11
     poesia
    -0.09
     filtering
    -0.09
    abla
    -0.08
     tagged
    -0.08
    po
    -0.08
     Roche
    -0.08
    _filtered
    -0.08
     कविता
    -0.08
     poesía
    -0.07
    POSITIVE LOGITS
    (iv
    0.08
     Total
    0.08
     dva
    0.08
     ശതമ
    0.08
     Federal
    0.08
     dog
    0.08
     amet
    0.08
     percentages
    0.08
     prosent
    0.08
     senator
    0.07
    Act Density 0.029%

    No Known Activations