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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    认识
    -0.08
    .setTo
    -0.07
    止损
    -0.07
    О
    -0.07
     monitor
    -0.07
    уча
    -0.07
     kHz
    -0.07
    /Dk
    -0.07
    kop
    -0.07
    Segment
    -0.07
    POSITIVE LOGITS
     mesure
    0.07
    吸
    0.07
     Later
    0.07
    гре
    0.07
    弟
    0.07
    érique
    0.07
    ינות
    0.07
     לעיתים
    0.06
    альных
    0.06
     lithium
    0.06
    Act Density 0.001%

    No Known Activations