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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Gal
    -0.07
    Extras
    -0.07
     elm
    -0.07
     gal
    -0.06
    _FEED
    -0.06
    988
    -0.06
    -insert
    -0.06
    ��
    -0.06
    _Profile
    -0.06
    ONENT
    -0.06
    POSITIVE LOGITS
     револю
    0.07
     había
    0.06
    虚
    0.06
     Seventh
    0.06
    -handed
    0.06
     Stripe
    0.06
     대학
    0.06
    感觉
    0.06
     короб
    0.06
     индивиду
    0.06
    Act Density 0.021%

    No Known Activations