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

    Neuronpedia

    INDEX
    Explanations

    Math word problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nghiền
    -0.08
     asparagus
    -0.08
     truncate
    -0.08
     भोज
    -0.08
    prits
    -0.07
    臣
    -0.07
     Bestandteil
    -0.07
    spiring
    -0.07
    fony
    -0.07
     कट
    -0.07
    POSITIVE LOGITS
     swings
    0.09
     состояни
    0.09
     saldo
    0.09
    Changes
    0.09
     fluctu
    0.08
    saldo
    0.08
    Saldo
    0.08
     trackers
    0.08
     togg
    0.08
     awal
    0.08
    Act Density 0.039%

    No Known Activations