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

    Neuronpedia

    INDEX
    Explanations

    Politics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     오
    -0.07
     зрост
    -0.07
     vlád
    -0.06
     Rapid
    -0.06
     thyroid
    -0.06
     людини
    -0.06
     ###
    -0.06
    Sec
    -0.06
     detector
    -0.06
     Ramp
    -0.06
    POSITIVE LOGITS
    kap
    0.07
    \Context
    0.07
     ${↵
    0.06
    alesce
    0.06
     зависим
    0.06
    'value
    0.06
     navCtrl
    0.06
    />.
    0.06
    ارة
    0.06
    毕
    0.06
    Act Density 0.038%

    No Known Activations