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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Explorer
    -0.07
     diagnostic
    -0.07
    -ref
    -0.07
     Fo
    -0.06
    енд
    -0.06
     Ul
    -0.06
     Mand
    -0.06
     Fame
    -0.06
    ldata
    -0.06
     CLICK
    -0.06
    POSITIVE LOGITS
     trest
    0.08
     مکان
    0.07
     thịt
    0.07
    _tb
    0.07
    /ubuntu
    0.07
     지금
    0.06
    опол
    0.06
     |--------------------------------------------------------------------------↵
    0.06
    ("---
    0.06
    需求
    0.06
    Act Density 0.072%

    No Known Activations