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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $stmt
    -0.07
     Pra
    -0.07
     Kup
    -0.07
     Av
    -0.06
     Ig
    -0.06
    _PI
    -0.06
    广
    -0.06
     historian
    -0.06
     Calendar
    -0.06
     zipper
    -0.06
    POSITIVE LOGITS
     fullfile
    0.06
     Το
    0.06
     cele
    0.06
     BITTE
    0.06
    TextNode
    0.06
    very
    0.06
    Alternatively
    0.06
     illumin
    0.06
     लगत
    0.06
     wirk
    0.06
    Act Density 0.118%

    No Known Activations