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

    Neuronpedia

    INDEX
    Explanations

    UB

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    çĬ¯
    -0.28
    ä»İ严
    -0.28
    éĻħ
    -0.26
    ç´«å¤ĸ
    -0.26
     duro
    -0.26
    åĶ®åIJİ
    -0.25
    maximum
    -0.25
     Classification
    -0.25
    judge
    -0.25
    udo
    -0.24
    POSITIVE LOGITS
     pts
    0.28
    .getContext
    0.27
     IDC
    0.26
    roid
    0.26
    åĽ½åľŁ
    0.26
    Thanks
    0.25
    éĿĻ
    0.24
    PTS
    0.24
    ounder
    0.24
     Pt
    0.23
    Act Density 0.380%

    No Known Activations