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

    Neuronpedia

    INDEX
    Explanations

    code and commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     które
    -0.07
    dbname
    -0.07
     Pune
    -0.07
    _Time
    -0.07
    리로
    -0.06
     paris
    -0.06
    .Mockito
    -0.06
     Snape
    -0.06
     Startup
    -0.06
     Veronica
    -0.06
    POSITIVE LOGITS
    ...
↵
    0.06
    ุด
    0.06
    صد
    0.06
    adě
    0.06
    _quad
    0.06
    (FILE
    0.06
    .callback
    0.06
     compromises
    0.06
     nắng
    0.06
    召
    0.06
    Act Density 0.004%

    No Known Activations