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

    Neuronpedia

    INDEX
    Explanations

    Hitting the mainstream

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    　　　　　　
    -0.07
    .Skip
    -0.06
     münchen
    -0.06
    {*
    -0.06
     athleticism
    -0.06
    nými
    -0.06
     nguy
    -0.06
    ちゃ
    -0.06
    $pdf
    -0.06
     Depending
    -0.06
    POSITIVE LOGITS
     Richt
    0.07
     mach
    0.07
     ally
    0.07
     sold
    0.06
    اقل
    0.06
    -п
    0.06
     сот
    0.06
     Ich
    0.06
     sell
    0.06
     tonic
    0.06
    Act Density 0.116%

    No Known Activations