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

    Neuronpedia

    INDEX
    Explanations

    190

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ינים
    -0.08
     necessária
    -0.08
     hallmark
    -0.08
     Machinery
    -0.08
     Closing
    -0.08
     pertinente
    -0.08
    _questions
    -0.07
     ERA
    -0.07
    _queries
    -0.07
     TREE
    -0.07
    POSITIVE LOGITS
    -size
    0.08
     غذا
    0.07
     суб
    0.07
     маль
    0.07
     ஆகிய
    0.07
     Meh
    0.07
     }},↵
    0.07
    held
    0.07
     punto
    0.07
    」という
    0.07
    Act Density 0.008%

    No Known Activations