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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ictionary
    -0.06
    舗
    -0.06
    istle
    -0.06
    izz
    -0.06
    	case
    -0.06
    ่าร
    -0.05
     территории
    -0.05
    Units
    -0.05
    IDX
    -0.05
    Idx
    -0.05
    POSITIVE LOGITS
    awan
    0.07
    лекс
    0.07
     Roads
    0.06
     electrodes
    0.06
     wherever
    0.06
     TODAY
    0.06
     Sinai
    0.06
     "'.
    0.06
     hurl
    0.06
    racuse
    0.06
    Act Density 0.169%

    No Known Activations