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

    Neuronpedia

    INDEX
    Explanations

    `"y":`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अभियांत्रिकी
    0.73
     masculino
    0.71
     Boyfriend
    0.71
     العديد
    0.70
     quantidades
    0.70
     කාල
    0.68
    ociaż
    0.68
    പാട്
    0.68
     movimientos
    0.68
     Еўропы
    0.68
    POSITIVE LOGITS
    ã
    0.65
    ĕ
    0.65
     thrives
    0.62
    9
    0.60
    TA
    0.57
    U
    0.56
     whose
    0.55
    ilh
    0.55
    TreeView
    0.55
    7
    0.54
    Act Density 0.021%

    No Known Activations