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

    Neuronpedia

    INDEX
    Explanations

    alternating rows

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gregg
    -0.07
     teammates
    -0.06
     ди
    -0.06
     Felix
    -0.06
     shepherd
    -0.06
     Zimmer
    -0.06
     marketers
    -0.06
    thal
    -0.06
     games
    -0.06
     Vermont
    -0.06
    POSITIVE LOGITS
     strtok
    0.07
    ROOT
    0.06
    朝
    0.06
     appropriately
    0.06
    toBeTruthy
    0.06
    :bg
    0.06
    _extract
    0.06
    _plural
    0.06
     استرات
    0.06
     aos
    0.06
    Act Density 0.136%

    No Known Activations