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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    order
    -0.06
     pobl
    -0.06
    enderit
    -0.06
     Orr
    -0.06
     carr
    -0.06
     Islanders
    -0.06
    父亲
    -0.06
     AsyncTask
    -0.06
    ucchini
    -0.06
    ITT
    -0.05
    POSITIVE LOGITS
     tipos
    0.07
    _conv
    0.07
     drag
    0.07
     وا
    0.06
     UPPER
    0.06
     свою
    0.06
    Foreground
    0.06
    nore
    0.06
    mono
    0.06
     Bike
    0.06
    Act Density 0.070%

    No Known Activations