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

    Neuronpedia

    INDEX
    Explanations

    anytime

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ul
    -0.08
     vel
    -0.07
     locks
    -0.06
     angels
    -0.06
     อ
    -0.06
     chtěl
    -0.06
     weighed
    -0.06
     oats
    -0.06
     briefly
    -0.06
     iz
    -0.06
    POSITIVE LOGITS
     fleet
    0.07
    (this
    0.06
    .Email
    0.06
    地址
    0.06
    Holiday
    0.06
    不过
    0.06
    	Value
    0.06
    한테
    0.06
     Naomi
    0.06
     Theft
    0.06
    Act Density 0.000%

    No Known Activations