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

    Neuronpedia

    INDEX
    Explanations

    background

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    irit
    -0.08
    bitr
    -0.07
    sible
    -0.07
     operating
    -0.07
     accomplishing
    -0.07
     instantaneous
    -0.07
    \↵
    -0.07
    され
    -0.07
     \↵
    -0.07
     operation
    -0.07
    POSITIVE LOGITS
    ாது
    0.09
     गर्द
    0.09
     clutter
    0.09
     виб
    0.08
     bustling
    0.08
    Muted
    0.08
     விட
    0.08
    łości
    0.08
     muted
    0.08
     اط
    0.08
    Act Density 0.004%

    No Known Activations