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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (hour
    -0.06
    optgroup
    -0.06
    charset
    -0.06
    ğimiz
    -0.06
     güzel
    -0.06
     gerne
    -0.06
     providers
    -0.06
     polygons
    -0.06
     Viet
    -0.06
    words
    -0.06
    POSITIVE LOGITS
    toFloat
    0.07
    -n
    0.06
     $↵
    0.06
     än
    0.06
     �
    0.06
     故
    0.06
    #else
    0.06
    โน
    0.06
    -transform
    0.06
     invitation
    0.06
    Act Density 0.001%

    No Known Activations