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

    Neuronpedia

    INDEX
    Explanations

    conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    comments
    -0.07
    tenir
    -0.07
     commented
    -0.07
    interpret
    -0.07
    _email
    -0.07
     Gmail
    -0.07
    Synopsis
    -0.07
    .mail
    -0.06
     consolid
    -0.06
     মন্তব্য
    -0.06
    POSITIVE LOGITS
     continuous
    0.09
     breat
    0.09
     :)↵
    0.09
     пуз
    0.09
     eenvoudige
    0.09
     ?><
    0.09
     Continuous
    0.08
     :)↵↵
    0.08
     manners
    0.08
     senc
    0.08
    Act Density 0.026%

    No Known Activations