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

    Neuronpedia

    INDEX
    Explanations

    references to other parts of the paper

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    findpost
    -0.99
     referenties
    -0.85
    antMatchers
    -0.80
     AspNetCore
    -0.77
    photobucket
    -0.75
    aarrggbb
    -0.73
    الإنجليزية
    -0.71
    исленность
    -0.69
    цездатний
    -0.69
    pyplot
    -0.68
    POSITIVE LOGITS
     ſeveral
    0.76
     ſhould
    0.74
     becauſe
    0.69
     themſelves
    0.68
     fevere
    0.66
     muſt
    0.66
     myſelf
    0.66
     leſs
    0.65
     pleaſure
    0.65
     itſelf
    0.65
    Act Density 0.119%

    No Known Activations