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

    Neuronpedia

    INDEX
    Explanations

    devices and apparatus

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (temp
    -0.07
    国务院
    -0.07
     objects
    -0.07
    future
    -0.07
    高等学校
    -0.07
    UIViewController
    -0.07
    ậ
    -0.07
    四大
    -0.07
    _TRIANGLES
    -0.07
     büyü
    -0.07
    POSITIVE LOGITS
    ancybox
    0.07
     ART
    0.07
    bl
    0.07
     Consultant
    0.06
    Outlined
    0.06
     graffiti
    0.06
    strftime
    0.06
    מאבק
    0.06
    iment
    0.06
    Đ
    0.06
    Act Density 0.045%

    No Known Activations