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

    Neuronpedia

    INDEX
    Explanations

    ib

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kon
    -0.07
     меш
    -0.07
     док
    -0.06
     inher
    -0.06
    _cate
    -0.06
    ρεί
    -0.06
    _patches
    -0.06
    	init
    -0.06
    ่อไป
    -0.06
    .EventType
    -0.06
    POSITIVE LOGITS
     Being
    0.07
     Council
    0.07
     exaggerated
    0.06
     banning
    0.06
    Being
    0.06
     Treaty
    0.06
     bow
    0.06
    million
    0.06
     wiped
    0.06
    "Well
    0.06
    Act Density 0.002%

    No Known Activations