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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     password
    -0.07
    اهيم
    -0.07
    -T
    -0.06
    +t
    -0.06
    enthal
    -0.06
    IsRequired
    -0.06
    	pw
    -0.06
    ัฐบาล
    -0.06
    extension
    -0.06
     승
    -0.06
    POSITIVE LOGITS
    �
    0.06
    신
    0.06
    خر
    0.06
     gear
    0.06
    .findIndex
    0.06
    yahoo
    0.06
    coll
    0.06
     dnů
    0.06
     Hond
    0.06
    .cleanup
    0.06
    Act Density 0.123%

    No Known Activations