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

    Neuronpedia

    INDEX
    Explanations

    Java code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    qe
    -0.07
     니
    -0.06
     meanwhile
    -0.06
    	friend
    -0.06
    -0.06
     voted
    -0.06
     account
    -0.06
     we
    -0.06
     sessionId
    -0.06
     underwear
    -0.06
    POSITIVE LOGITS
     Sophie
    0.07
    是个
    0.07
     explosive
    0.07
    임
    0.06
    .DropDownList
    0.06
    '*
    0.06
     BlackBerry
    0.06
    .DrawString
    0.06
    .response
    0.06
    prises
    0.06
    Act Density 0.015%

    No Known Activations