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

    Neuronpedia

    INDEX
    Explanations

    default

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    564
    -0.08
    =DB
    -0.08
    657
    -0.08
    369
    -0.07
     distributed
    -0.07
    posta
    -0.07
    864
    -0.07
    Contains
    -0.07
     offsetX
    -0.06
    овано
    -0.06
    POSITIVE LOGITS
    	back
    0.06
     müda
    0.06
     thí
    0.06
      ↵
    0.06
     viết
    0.06
    ct
    0.06
     fluctuations
    0.06
    ิธ
    0.06
    Fourth
    0.06
     Sym
    0.05
    Act Density 0.000%

    No Known Activations