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

    Neuronpedia

    INDEX
    Explanations

    IT, HR, ECS, presence, page

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    یس
    0.53
    haman
    0.48
    րան
    0.47
    osity
    0.47
    iless
    0.46
    த்திற்காக
    0.45
    ствовали
    0.45
    aranth
    0.44
    ocap
    0.44
    ocused
    0.43
    POSITIVE LOGITS
    XML
    0.49
     দূর
    0.44
    想像
    0.43
     దూ
    0.43
     यात
    0.42
    鑄
    0.42
     걸
    0.42
     الر
    0.41
     civilization
    0.41
    plätze
    0.41
    Act Density 0.010%

    No Known Activations