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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     routinely
    -0.07
     Parker
    -0.07
     bahwa
    -0.07
    finder
    -0.06
     вра
    -0.06
     القانون
    -0.06
    venes
    -0.06
    buquerque
    -0.06
    Writing
    -0.06
    артам
    -0.06
    POSITIVE LOGITS
    /tiny
    0.06
    .m
    0.06
     sapi
    0.06
     enthusiasm
    0.06
    createTime
    0.06
    .commit
    0.06
    rawtypes
    0.06
     sophistication
    0.06
     Manga
    0.06
     collo
    0.06
    Act Density 0.035%

    No Known Activations