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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rios
    -0.08
     Lle
    -0.08
     reportage
    -0.07
     अनेक
    -0.07
     hydrox
    -0.07
    支付宝
    -0.07
     wass
    -0.07
    reibung
    -0.07
    :maj
    -0.07
    Reasons
    -0.07
    POSITIVE LOGITS
     zichzelf
    0.10
     자기
    0.10
     sarili
    0.09
     الذات
    0.09
     engager
    0.08
     zelfstandig
    0.08
     vanzelf
    0.08
    নিজ
    0.08
     vanaf
    0.08
     dishonest
    0.08
    Act Density 0.011%

    No Known Activations