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

    Neuronpedia

    INDEX
    Explanations

    Medical treatments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("."
    -0.07
     Conscious
    -0.06
    plně
    -0.06
    鸡
    -0.06
    Patrick
    -0.06
    iều
    -0.06
     vary
    -0.06
    (Request
    -0.06
    นำ
    -0.06
    最佳
    -0.06
    POSITIVE LOGITS
     processors
    0.07
     toler
    0.07
     expelled
    0.06
     easing
    0.06
    系列
    0.06
     raison
    0.06
    Pa
    0.06
    olerance
    0.06
     xi
    0.06
    lds
    0.06
    Act Density 0.153%

    No Known Activations