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

    Neuronpedia

    INDEX
    Explanations

    financial regulations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    빈
    -0.07
     marker
    -0.07
    (marker
    -0.07
    .marker
    -0.07
     oblik
    -0.07
    zek
    -0.07
    lim
    -0.07
    decorate
    -0.07
    (mc
    -0.07
     limiting
    -0.07
    POSITIVE LOGITS
     Ausbildung
    0.09
     [&
    0.09
    怒
    0.08
    icipant
    0.08
     tao
    0.08
    骤
    0.08
     tj
    0.08
     Thats
    0.08
     Told
    0.08
     ڇا
    0.08
    Act Density 0.000%

    No Known Activations