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

    Neuronpedia

    INDEX
    Explanations

    Times in minutes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ure
    -0.07
    ité
    -0.07
    汽车
    -0.07
     Vista
    -0.07
     newArray
    -0.06
    ция
    -0.06
     fname
    -0.06
     choices
    -0.06
    难
    -0.06
    英语
    -0.06
    POSITIVE LOGITS
    .*,
    0.06
    -aligned
    0.06
    605
    0.06
     gracefully
    0.06
    adays
    0.06
     negot
    0.06
     annot
    0.06
     either
    0.06
    Phil
    0.06
    SEP
    0.06
    Act Density 0.018%

    No Known Activations