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

    Neuronpedia

    INDEX
    Explanations

    Internet Corporation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Yucatán
    0.47
    図書館
    0.47
    ERO
    0.46
    María
    0.45
    ڦ
    0.45
     случи
    0.45
    㝌
    0.45
    lifer
    0.43
    番
    0.42
    титься
    0.42
    POSITIVE LOGITS
     Technologie
    0.46
    genic
    0.44
     darkening
    0.44
    eneration
    0.44
    ères
    0.44
     for
    0.43
     Clarke
    0.43
     avoid
    0.43
    #%%
    0.43
     Oxide
    0.42
    Act Density 0.096%

    No Known Activations