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

    Neuronpedia

    INDEX
    Explanations

    Technical systems and operation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Тер
    -0.07
    Donald
    -0.07
    دة
    -0.06
    grade
    -0.06
     فر
    -0.06
    :eq
    -0.06
    иру
    -0.06
    енсив
    -0.06
    riculum
    -0.06
     planting
    -0.06
    POSITIVE LOGITS
     absl
    0.08
    _geometry
    0.06
    		
↵		
↵
    0.06
     Crate
    0.06
    ↵   ↵
    0.06
    到的
    0.06
     právo
    0.06
    .MenuStrip
    0.06
     strs
    0.06
     multiplier
    0.06
    Act Density 0.040%

    No Known Activations