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

    Neuronpedia

    INDEX
    Explanations

    code delimiters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "***
    -0.06
     lombok
    -0.06
     cries
    -0.06
    /int
    -0.06
    (det
    -0.06
     beh
    -0.06
     حتى
    -0.06
    iran
    -0.06
     dar
    -0.06
    hhh
    -0.06
    POSITIVE LOGITS
    erview
    0.07
    _Work
    0.06
    cedure
    0.06
     Achievement
    0.06
    Connecting
    0.06
    ETwitter
    0.06
    丁目
    0.06
     posts
    0.06
    -flex
    0.06
    coni
    0.06
    Act Density 0.008%

    No Known Activations