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

    Neuronpedia

    INDEX
    Explanations

    before

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    amse
    -0.08
    izens
    -0.07
    ablemente
    -0.07
     Players
    -0.07
     odp
    -0.07
    -ek
    -0.07
    esm
    -0.07
    ivatives
    -0.07
     stadig
    -0.07
     nicely
    -0.07
    POSITIVE LOGITS
     vs
    0.09
    (before
    0.09
     versus
    0.08
     problematic
    0.08
     untreated
    0.08
     baseline
    0.08
     праблем
    0.08
     lösen
    0.08
     проблемы
    0.08
     проблем
    0.08
    Act Density 0.017%

    No Known Activations