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
     schematic
    -0.07
     طرح
    -0.07
     dynamic
    -0.07
     scheme
    -0.07
    vis
    -0.07
     escape
    -0.07
    ប
    -0.07
    -0.07
     recom
    -0.07
     divis
    -0.07
    POSITIVE LOGITS
     শুক্রবার
    0.10
     시작
    0.10
     શરૂ
    0.10
     అంటూ
    0.10
     başlan
    0.10
     শুরু
    0.09
     boshl
    0.09
     başlayan
    0.09
     शुर
    0.09
     week's
    0.09
    Act Density 0.093%
    No Known Activations