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

    Neuronpedia

    INDEX
    Explanations

    parenthesis and semicolons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    리지
    -0.07
    structure
    -0.06
     수도
    -0.06
    partner
    -0.06
    료
    -0.06
    bbie
    -0.06
    itches
    -0.06
    ubu
    -0.06
    ��
    -0.06
    短
    -0.06
    POSITIVE LOGITS
     adapt
    0.06
     sailed
    0.06
    __))↵
    0.06
     epith
    0.06
     writings
    0.06
     freq
    0.06
     ymin
    0.06
     fathers
    0.06
    /／
    0.06
     assort
    0.06
    Act Density 0.072%

    No Known Activations