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

    Neuronpedia

    INDEX
    Explanations

    has

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    emoth
    -0.07
    raisal
    -0.07
    	QString
    -0.06
    커
    -0.06
    σμό
    -0.06
    larınız
    -0.06
     Lawson
    -0.06
     nấu
    -0.06
     FHA
    -0.06
    orrow
    -0.06
    POSITIVE LOGITS
     permissions
    0.07
    CAM
    0.06
     ATH
    0.06
    죽
    0.06
     Dram
    0.06
     слова
    0.06
    Ο
    0.06
     konce
    0.06
    odium
    0.06
    prim
    0.06
    Act Density 0.158%

    No Known Activations