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

    Neuronpedia

    INDEX
    Explanations

    роме

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     themselves
    -0.07
     often
    -0.06
     scrolling
    -0.06
    ozor
    -0.06
     fet
    -0.06
     Often
    -0.06
    ewhat
    -0.06
    ,assign
    -0.06
     озна
    -0.06
     repeatedly
    -0.06
    POSITIVE LOGITS
     Кроме
    0.10
    TableName
    0.07
     кроме
    0.07
    =test
    0.07
    PORT
    0.07
    _Query
    0.06
    .Space
    0.06
     pathways
    0.06
     curriculum
    0.06
    <table
    0.06
    Act Density 0.001%

    No Known Activations