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
    ppel
    -0.08
    Inspir
    -0.08
    859
    -0.08
     MAIS
    -0.08
    .instances
    -0.08
    764
    -0.08
    (inflater
    -0.08
     нашим
    -0.08
     referentes
    -0.08
     ягод
    -0.08
    POSITIVE LOGITS
     computations
    0.08
     measurement
    0.08
    -less
    0.08
     fidelity
    0.07
     erroneous
    0.07
    之间
    0.07
     relationship
    0.07
     efficiencies
    0.07
    之外
    0.07
    间
    0.07
    Act Density 0.223%

    No Known Activations