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

    Neuronpedia

    INDEX
    Explanations

    offer help

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     freely
    0.83
     ill
    0.82
     constricted
    0.80
    кә
    0.73
    इ
    0.73
     dead
    0.73
    ﹣
    0.71
     Siege
    0.71
     lieben
    0.70
     ayud
    0.70
    POSITIVE LOGITS
     Ư
    0.89
    格兰
    0.85
     Sử
    0.85
     Các
    0.84
     С
    0.78
     เมือง
    0.78
     Umsetzung
    0.78
     Durchführung
    0.78
     Employers
    0.77
     Così
    0.76
    Act Density 0.000%

    No Known Activations