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

    Neuronpedia

    INDEX
    Explanations

    publication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (folder
    -0.07
    StandardItem
    -0.07
    (Get
    -0.07
     matlab
    -0.06
    (values
    -0.06
    .WinControls
    -0.06
    ANNER
    -0.06
     <=>
    -0.06
    RL
    -0.06
     rise
    -0.06
    POSITIVE LOGITS
    undai
    0.07
     giveaways
    0.06
    little
    0.06
    27
    0.06
    official
    0.06
    "display
    0.06
     زیادی
    0.06
     użytk
    0.06
    6
    0.06
    ประช
    0.06
    Act Density 0.021%

    No Known Activations