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
     literacy
    -0.08
    -responsive
    -0.08
     liter
    -0.08
    _reviews
    -0.07
    _received
    -0.07
    ള്
    -0.07
     Reviews
    -0.07
    reviews
    -0.07
     sze
    -0.07
    Responsive
    -0.07
    POSITIVE LOGITS
     verläng
    0.12
     beyond
    0.11
     خارج
    0.11
     extending
    0.11
     außerhalb
    0.11
     Beyond
    0.10
     Extend
    0.09
    Extend
    0.09
     distant
    0.09
    -delà
    0.09
    Act Density 0.049%

    No Known Activations