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

    Neuronpedia

    INDEX
    Explanations

    production

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    README
    -0.07
     Tig
    -0.06
     enslaved
    -0.06
    zing
    -0.06
    option
    -0.06
     Pall
    -0.06
     ăn
    -0.06
    ้าก
    -0.06
     Tasks
    -0.06
     slide
    -0.06
    POSITIVE LOGITS
    ':[
    0.06
    =?";↵
    0.06
    ::|
    0.06
    [...,
    0.06
    .charAt
    0.06
     globally
    0.06
    dm
    0.06
    structural
    0.06
     funnel
    0.06
    .qq
    0.06
    Act Density 0.031%

    No Known Activations