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

    Neuronpedia

    INDEX
    Explanations

    when

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tees
    -0.07
     bil
    -0.07
    ivirus
    -0.07
    {x
    -0.07
    ctxt
    -0.07
    .resources
    -0.07
    _bt
    -0.07
     privat
    -0.07
    ang
    -0.07
     III
    -0.07
    POSITIVE LOGITS
    Ế
    0.06
     복
    0.06
     ederek
    0.06
     baptism
    0.06
     unrealistic
    0.06
    我們
    0.06
    μι
    0.06
    	Document
    0.05
     capt
    0.05
     launcher
    0.05
    Act Density 0.030%

    No Known Activations