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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Karnataka
    -0.07
     acordo
    -0.07
     Superior
    -0.06
    })"↵
    -0.06
    dato
    -0.06
    -F
    -0.06
     formas
    -0.06
     ordinal
    -0.06
     Myers
    -0.06
     polym
    -0.06
    POSITIVE LOGITS
     (`
    0.07
     crushers
    0.06
    ?>>
    0.06
    incare
    0.06
    िनट
    0.06
    ...
    0.06
    %!
    0.06
    uppies
    0.06
     років
    0.06
     arranged
    0.06
    Act Density 0.008%

    No Known Activations