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

    Neuronpedia

    INDEX
    Explanations

    need

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ngon
    -0.08
     vượt
    -0.08
    .blog
    -0.08
     capable
    -0.08
    ાઓ
    -0.08
    sampling
    -0.08
     vast
    -0.08
    авед
    -0.08
     voorlop
    -0.08
     �
    -0.07
    POSITIVE LOGITS
     beachten
    0.08
     Clar
    0.08
     genauer
    0.08
    确认
    0.08
     probably
    0.08
     disgr
    0.08
     כי
    0.08
     Probably
    0.08
    Clar
    0.07
     уточ
    0.07
    Act Density 0.032%

    No Known Activations