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

    Neuronpedia

    INDEX
    Explanations

    resists the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Were
    0.94
     પરંતુ
    0.82
     Were
    0.78
     لیکن
    0.78
     。,
    0.77
    Ста
    0.77
    ։
    0.75
    哦
    0.74
    喔
    0.71
     ஆகியோர்
    0.70
    POSITIVE LOGITS
     represents
    3.19
     tends
    3.13
     provides
    3.12
     relies
    3.08
     doesn
    3.08
     gives
    3.06
     brings
    3.01
     requires
    3.00
     comes
    3.00
     allows
    2.97
    Act Density 1.676%

    No Known Activations