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

    Neuronpedia

    INDEX
    Explanations

    attraction is free

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Linux
    0.99
     Byzant
    0.92
     Python
    0.91
     Cherokee
    0.88
     VMware
    0.84
     AMD
    0.83
     Unicode
    0.83
     MATLAB
    0.83
     HubSpot
    0.83
     AWS
    0.82
    POSITIVE LOGITS
    _
    1.44
    \_
    1.01
     देतात
    0.97
    Rating
    0.94
     भत्ता
    0.94
    ourent
    0.91
     decidiu
    0.88
    <unused62>
    0.88
    %'
    0.87
     varchar
    0.86
    Act Density 1.162%

    No Known Activations