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

    Neuronpedia

    INDEX
    Explanations

    reviews/opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     festive
    -0.07
     Notifications
    -0.06
    sandbox
    -0.06
     romantic
    -0.06
     gathers
    -0.06
     parl
    -0.06
     accepted
    -0.06
     Phòng
    -0.06
     Sony
    -0.06
     polic
    -0.06
    POSITIVE LOGITS
    ,},↵
    0.07
     Erg
    0.07
     množ
    0.07
     bağlantılar
    0.06
    居
    0.06
    ,%
    0.06
     Sb
    0.06
     `}↵
    0.06
     ()
    0.06
    (done
    0.06
    Act Density 0.067%

    No Known Activations