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

    Neuronpedia

    INDEX
    Explanations

    Quotation and commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vener
    -0.08
     elk
    -0.08
     APR
    -0.08
     Ama
    -0.07
    roo
    -0.07
    ibel
    -0.07
    ומת
    -0.07
    controls
    -0.07
    viron
    -0.07
     physics
    -0.07
    POSITIVE LOGITS
     గా
    0.08
     poetry
    0.08
     refers
    0.08
     కాదు
    0.08
     کل
    0.07
     колес
    0.07
     бро
    0.07
     assez
    0.07
     به
    0.07
     называют
    0.07
    Act Density 0.039%

    No Known Activations