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

    Neuronpedia

    INDEX
    Explanations

    Maven dependency declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    identité
    0.92
     منف
    0.88
    აცი
    0.85
    uttu
    0.84
     Вай
    0.83
    štění
    0.82
     Plut
    0.81
     प्ला
    0.81
    蝕
    0.80
    榫
    0.80
    POSITIVE LOGITS
     management
    0.75
     <
    0.68
    <tr>
    0.66
     road
    0.64
     managers
    0.64
    |^
    0.62
     Management
    0.61
    Management
    0.61
     streak
    0.60
    <td>
    0.60
    Act Density 0.001%

    No Known Activations