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

    Neuronpedia

    INDEX
    Explanations

    Foundation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     تومان
    -0.08
    ▋
    -0.07
     olacaktır
    -0.07
     otra
    -0.07
     beş
    -0.06
     ISC
    -0.06
     můžeme
    -0.06
    -Y
    -0.06
     Amazing
    -0.06
     contraseña
    -0.06
    POSITIVE LOGITS
    Union
    0.08
    -multi
    0.07
     unwind
    0.07
    foundation
    0.07
    icated
    0.07
     companion
    0.07
    อป
    0.07
     movement
    0.07
     muted
    0.07
     uniformly
    0.06
    Act Density 0.003%

    No Known Activations