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

    Neuronpedia

    INDEX
    Explanations

    Rehearing denied

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    İs
    -0.07
     triples
    -0.07
    -abortion
    -0.07
    ecute
    -0.07
    ographies
    -0.06
    _g
    -0.06
    галтер
    -0.06
    -Ф
    -0.06
     Show
    -0.06
    umper
    -0.06
    POSITIVE LOGITS
    طل
    0.07
     حض
    0.06
     خط
    0.06
     갤로그
    0.06
     reste
    0.06
     прос
    0.06
     thinly
    0.06
     NAFTA
    0.06
     compreh
    0.06
    ricane
    0.06
    Act Density 0.015%

    No Known Activations