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

    Neuronpedia

    INDEX
    Explanations

    Dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ucwords
    -0.07
    InterfaceOrientation
    -0.06
     Eid
    -0.06
     rowspan
    -0.06
    ũi
    -0.06
    ̉
    -0.06
     Angle
    -0.06
     DatabaseReference
    -0.06
     Mario
    -0.06
     законом
    -0.06
    POSITIVE LOGITS
     vitamin
    0.07
    NIL
    0.06
     stanov
    0.06
    )b
    0.06
     NYT
    0.06
    robot
    0.06
    **,
    0.06
    kees
    0.06
    렸다
    0.06
     yum
    0.06
    Act Density 0.046%

    No Known Activations