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

    Neuronpedia

    INDEX
    Explanations

    Math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    beck
    -0.07
    .•
    -0.07
    atic
    -0.06
    cede
    -0.06
    ATIC
    -0.06
     Specifications
    -0.06
    Son
    -0.06
    Lat
    -0.06
     две
    -0.06
    ERRU
    -0.06
    POSITIVE LOGITS
     пит
    0.07
     СССР
    0.07
     оно
    0.06
    สามารถ
    0.06
    SJ
    0.06
     presumably
    0.06
     Ч
    0.06
     öncelik
    0.06
     [[]
    0.06
     jeune
    0.06
    Act Density 0.012%

    No Known Activations