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

    Neuronpedia

    INDEX
    Explanations

    DX and CX advancement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     キッズ
    0.43
     nuevo
    0.42
    án
    0.41
    ritz
    0.41
    ારે
    0.40
     chicos
    0.40
     nueva
    0.40
    rable
    0.39
     přímo
    0.39
    yecto
    0.38
    POSITIVE LOGITS
    فاع
    0.46
     kompleks
    0.45
     sceptical
    0.45
     corporations
    0.44
     Corporations
    0.43
     corporation
    0.42
    AppendLine
    0.42
     akhir
    0.42
     appass
    0.41
    Corpor
    0.41
    Act Density 0.001%

    No Known Activations