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

    Neuronpedia

    INDEX
    Explanations

    economic arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     समाय
    0.41
    νου
    0.41
     부족
    0.40
     विद्य
    0.39
    slim
    0.38
    DeleteDialogOpen
    0.38
    ቼ
    0.38
    ieri
    0.37
    naj
    0.37
    三角
    0.37
    POSITIVE LOGITS
     Sustainable
    0.45
    Sustainable
    0.44
     масшта
    0.41
    ̉
    0.40
    ەڕ
    0.39
     substr
    0.38
    可持续
    0.38
     eril
    0.38
     sustainable
    0.37
     Kall
    0.37
    Act Density 0.000%

    No Known Activations