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

    Neuronpedia

    INDEX
    Explanations

    code comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     educated
    -0.07
     kennenlernen
    -0.07
    .While
    -0.07
     reporting
    -0.06
    .AddColumn
    -0.06
    084
    -0.06
    �
    -0.06
     optimism
    -0.06
     giảm
    -0.06
     Ethnic
    -0.06
    POSITIVE LOGITS
     значительно
    0.07
     مول
    0.06
     pomoc
    0.06
     slideshow
    0.06
     ((_
    0.06
    erial
    0.06
    (jj
    0.06
     JMP
    0.06
    toUpperCase
    0.06
    فر
    0.06
    Act Density 0.016%

    No Known Activations