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

    Neuronpedia

    INDEX
    Explanations

    bypass

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dicts
    -0.06
    なお
    -0.06
    солют
    -0.06
     yerel
    -0.06
    nete
    -0.06
     infections
    -0.06
    _doc
    -0.06
    _FLAG
    -0.06
     Wahl
    -0.06
     parlament
    -0.06
    POSITIVE LOGITS
    -pass
    0.07
     bö
    0.07
     -*-
    0.07
    (high
    0.07
     suppliers
    0.07
     CPR
    0.06
     cellForRowAtIndexPath
    0.06
    -heading
    0.06
     συνέ
    0.06
     routines
    0.06
    Act Density 0.001%

    No Known Activations