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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disks
    -0.07
     филь
    -0.07
     tình
    -0.07
    kladní
    -0.07
    _pressed
    -0.07
    307
    -0.06
    swire
    -0.06
    ');↵
    -0.06
    /mysql
    -0.06
     ',↵
    -0.06
    POSITIVE LOGITS
     baiser
    0.07
     ocup
    0.06
     giám
    0.06
     üçüncü
    0.06
    iế
    0.06
    textView
    0.06
    塚
    0.06
     Hollow
    0.06
    335
    0.05
     va
    0.05
    Act Density 0.001%

    No Known Activations