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

    Neuronpedia

    INDEX
    Explanations

    say "=" or "."

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مقر
    -0.09
     agarr
    -0.08
     GAN
    -0.08
    وق
    -0.08
     Kenny
    -0.07
     משת
    -0.07
    (pin
    -0.07
    īgi
    -0.07
     chair
    -0.07
     Coordin
    -0.07
    POSITIVE LOGITS
     separates
    0.09
     }}>↵
    0.08
    Separate
    0.08
    Flows
    0.08
     "=
    0.08
    Shortcut
    0.08
     harimo
    0.08
     Перв
    0.08
     अधिकांश
    0.08
    divide
    0.08
    Act Density 0.032%

    No Known Activations