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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    packages
    -0.06
     sentences
    -0.06
     Sensors
    -0.06
    "):↵
    -0.06
    $username
    -0.06
    _source
    -0.06
     movies
    -0.06
     natives
    -0.06
    569
    -0.06
    -alpha
    -0.06
    POSITIVE LOGITS
     ['',
    0.07
    무
    0.07
    ję
    0.07
    lef
    0.07
     eksik
    0.06
     }];↵↵
    0.06
     (?,
    0.06
    empre
    0.06
    RET
    0.06
     tainted
    0.06
    Act Density 0.011%

    No Known Activations