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

    Neuronpedia

    INDEX
    Explanations

    24

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    joined
    -0.07
     shuffled
    -0.06
    毛
    -0.06
    	List
    -0.06
    營
    -0.06
    _Normal
    -0.06
     jams
    -0.06
    *',
    -0.06
    .monitor
    -0.06
     أج
    -0.06
    POSITIVE LOGITS
    372
    0.07
    ETERS
    0.07
     useless
    0.06
    رفت
    0.06
    _MESSAGES
    0.06
    flatten
    0.06
     hombres
    0.06
     Medic
    0.06
     ca
    0.06
    พล
    0.06
    Act Density 0.010%

    No Known Activations