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

    Neuronpedia

    INDEX
    Explanations

    particular branch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (!
    1.03
    pon
    0.97
    onate
    0.97
     scan
    0.93
     pens
    0.93
     pin
    0.91
     Pamp
    0.90
     ancient
    0.90
     (/
    0.88
     Christmas
    0.88
    POSITIVE LOGITS
    <h3>
    1.36
    MDA
    1.27
    」。
    1.16
    <h4>
    1.11
    Corresponding
    1.09
    "}
    1.09
    <h2>
    1.09
    Localized
    1.08
    RL
    1.07
    "].
    1.06
    Act Density 1.224%

    No Known Activations