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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LOOK
    -0.06
    ylum
    -0.06
     цен
    -0.06
     DAMAGES
    -0.06
     Retail
    -0.06
    ินเด
    -0.06
    _meta
    -0.06
     videos
    -0.06
     چیز
    -0.06
     URLs
    -0.06
    POSITIVE LOGITS
    albums
    0.07
    .Rotate
    0.07
     unexpectedly
    0.06
    Until
    0.06
    _AUT
    0.06
    .HCM
    0.06
    (Initialized
    0.06
     düny
    0.06
    兼
    0.06
     Aph
    0.06
    Act Density 0.085%

    No Known Activations