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

    Neuronpedia

    INDEX
    Explanations

    ->

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lines
    -0.08
     professor
    -0.07
    ,this
    -0.07
     enchanted
    -0.07
     myList
    -0.07
     typography
    -0.07
     🙂↵↵
    -0.07
    	FILE
    -0.07
    ])↵↵
    -0.06
     Decision
    -0.06
    POSITIVE LOGITS
    оген
    0.06
     Теп
    0.06
    icable
    0.06
     собира
    0.06
     liệt
    0.06
     aliases
    0.06
     وجود
    0.06
    يمكن
    0.06
     نش
    0.06
     طول
    0.06
    Act Density 0.002%

    No Known Activations