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
     पैदा
    -0.08
     açısından
    -0.07
     unsafe
    -0.07
     पहुंच
    -0.07
     Gramm
    -0.07
     favoris
    -0.07
     કાઢ
    -0.06
    最准
    -0.06
    /select
    -0.06
     Rubber
    -0.06
    POSITIVE LOGITS
     ergän
    0.09
     دا
    0.09
     části
    0.08
     restantes
    0.08
     동안
    0.08
    .stage
    0.08
     condolences
    0.08
     후
    0.08
     recount
    0.08
     portion
    0.08
    Act Density 0.061%

    No Known Activations