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
    ிம
    -0.08
    ptember
    -0.08
    χη
    -0.08
    碑
    -0.07
    decess
    -0.07
     આધ
    -0.07
    琪
    -0.07
    /change
    -0.07
     روم
    -0.07
    Slim
    -0.07
    POSITIVE LOGITS
     enlist
    0.08
     പ്രത്യേ
    0.08
     ഉണ്ട
    0.08
     proxies
    0.08
     മാത്ര
    0.07
     afo
    0.07
     counts
    0.07
     assessor
    0.07
    .callbacks
    0.07
    .count
    0.07
    Act Density 0.058%

    No Known Activations