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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    тия
    -0.07
     chronological
    -0.06
     Guantanamo
    -0.06
    _blend
    -0.06
    -public
    -0.06
    	Dictionary
    -0.06
    .setFill
    -0.06
     马
    -0.06
     gerekli
    -0.06
     рабоч
    -0.06
    POSITIVE LOGITS
     речі
    0.06
    _ssh
    0.06
    реп
    0.06
    /]
    0.06
     ADV
    0.06
    еку
    0.06
     converged
    0.06
    astically
    0.06
     Plugins
    0.06
     ip
    0.06
    Act Density 0.025%

    No Known Activations