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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    asse
    -0.08
     wartet
    -0.08
    انون
    -0.08
     కాల
    -0.08
    "),↵↵
    -0.07
     stemmen
    -0.07
     parliamentary
    -0.07
    October
    -0.07
    <Character
    -0.07
    }");↵↵
    -0.07
    POSITIVE LOGITS
     pesada
    0.09
     lourd
    0.08
    0.07
    /s
    0.07
     fout
    0.07
     Show
    0.07
     vic
    0.07
    /sw
    0.07
     sul
    0.07
     js
    0.07
    Act Density 0.024%
    No Known Activations