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

    Neuronpedia

    INDEX
    Explanations

    upstairs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Vert
    -0.07
    she
    -0.07
    认真
    -0.07
     encountered
    -0.07
    ricula
    -0.07
    -0.07
     unpack
    -0.07
     האינטרנט
    -0.06
     gathers
    -0.06
     encounter
    -0.06
    POSITIVE LOGITS
    言えば
    0.09
     فقط
    0.07
    assertSame
    0.07
    速度快
    0.07
    โบราณ
    0.06
    fb
    0.06
    ત
    0.06
    =title
    0.06
    _sender
    0.06
    켑
    0.06
    Act Density 0.006%

    No Known Activations