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

    Neuronpedia

    INDEX
    Explanations

    Javascript code using promises and async/await

    oai_token-act-pair · gemini-2.0-flash

    parenthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.81
     defaultstate
    -0.81
     pleaſure
    -0.80
    rrggbb
    -0.79
    SBATCH
    -0.77
    UnusedPrivate
    -0.77
     صوتيه
    -0.77
     Vikipedi
    -0.76
    τως
    -0.75
    urlpatterns
    -0.75
    POSITIVE LOGITS
     by
    0.53
    ”
    0.49
    j
    0.48
     useSelector
    0.48
     che
    0.47
    ,
    0.46
    “
    0.45
     J
    0.44
     }}"
    0.44
     K
    0.43
    Act Density 0.359%

    No Known Activations