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

    Neuronpedia

    INDEX
    Explanations

    Code/programming snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     taxa
    -0.07
     stark
    -0.07
     consign
    -0.07
     nylon
    -0.07
     aligns
    -0.07
     mate
    -0.07
     PSD
    -0.07
    ීම
    -0.07
     aliqu
    -0.07
     Billing
    -0.07
    POSITIVE LOGITS
    ‌తో
    0.08
    hul
    0.08
     Reactor
    0.08
    忘初心
    0.08
    prakt
    0.08
     Interior
    0.08
     glo
    0.08
     Му
    0.08
     ప్రముఖ
    0.07
    رل
    0.07
    Act Density 0.000%

    No Known Activations