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
    fax
    -0.07
    نامج
    -0.07
    _robot
    -0.07
    (binary
    -0.06
    _digest
    -0.06
    Memory
    -0.06
    Dig
    -0.06
    Firebase
    -0.06
     iron
    -0.06
    	router
    -0.06
    POSITIVE LOGITS
     Released
    0.06
     Tropical
    0.06
     inade
    0.06
    Hong
    0.06
     tropical
    0.06
     blazing
    0.06
     enclosing
    0.06
    -st
    0.05
    име
    0.05
     erotica
    0.05
    Act Density 0.031%

    No Known Activations