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

    Neuronpedia

    INDEX
    Explanations

    animals –

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’!
    0.94
    "!
    0.93
    <unused2164>
    0.90
    <unused2130>
    0.89
    ”!
    0.88
    </strong>
    0.87
    <unused2172>
    0.85
    <unused2125>
    0.82
     geospatial
    0.82
    ".
    0.80
    POSITIVE LOGITS
    ##
    0.95
    >>,
    0.93
    ####
    0.89
    [/
    0.88
    }{\
    0.87
    */
    0.85
    [[
    0.85
    */)
    0.84
    //}
    0.84
    《
    0.83
    Act Density 1.593%

    No Known Activations