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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CAPE
    -0.08
    龙门
    -0.08
    פה
    -0.07
     propelled
    -0.07
    בוט
    -0.07
     SPA
    -0.07
    comma
    -0.07
    -price
    -0.07
     Trash
    -0.07
    窊
    -0.07
    POSITIVE LOGITS
    	print
    0.08
     cont
    0.08
     Os
    0.07
    stdio
    0.07
     aut
    0.07
     whispered
    0.06
    .adj
    0.06
    だが
    0.06
    _Metadata
    0.06
    Car
    0.06
    Act Density 0.000%

    No Known Activations