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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     च
    -0.06
     unfolds
    -0.06
     hasNext
    -0.06
     tzv
    -0.06
     sides
    -0.06
     auditor
    -0.06
    -resources
    -0.05
    umlah
    -0.05
     коллек
    -0.05
     ú
    -0.05
    POSITIVE LOGITS
    	trigger
    0.07
     mö
    0.07
    film
    0.07
    ReLU
    0.07
    =g
    0.07
    MENTS
    0.07
    де
    0.07
    ："
    0.07
    	admin
    0.06
    ments
    0.06
    Act Density 0.095%

    No Known Activations