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

    Neuronpedia

    INDEX
    Explanations

    screen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    avel
    -0.06
     igen
    -0.06
     crian
    -0.06
     cruc
    -0.06
     prostitu
    -0.06
    нар
    -0.06
     kommer
    -0.06
     rahat
    -0.06
     askeri
    -0.06
    宗
    -0.06
    POSITIVE LOGITS
    archical
    0.07
     ROM
    0.06
    attendance
    0.06
     worthy
    0.06
    егодня
    0.06
    IOS
    0.06
    сом
    0.06
     reinstall
    0.06
    UBLISH
    0.06
    怎
    0.06
    Act Density 0.005%

    No Known Activations