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

    Neuronpedia

    INDEX
    Explanations

    law

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MEMORY
    -0.07
    >#
    -0.07
     information
    -0.06
    png
    -0.06
     sev
    -0.06
    902
    -0.06
    Just
    -0.06
    _allocated
    -0.06
    924
    -0.06
     torture
    -0.06
    POSITIVE LOGITS
     Damen
    0.06
     stad
    0.06
     kah
    0.06
     Nacional
    0.06
    .JSONArray
    0.06
    ▍
    0.06
    askell
    0.06
    солют
    0.06
     zákona
    0.06
    フト
    0.06
    Act Density 0.010%

    No Known Activations