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

    Neuronpedia

    INDEX
    Explanations

    technical processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AUX
    -0.07
     необ
    -0.07
    虽然
    -0.06
    越
    -0.06
     autoload
    -0.06
     =================
    -0.06
    ologically
    -0.06
     hemos
    -0.06
     dünyanın
    -0.06
    _learn
    -0.06
    POSITIVE LOGITS
    _five
    0.07
     تحميل
    0.07
    ètre
    0.06
    elaide
    0.06
     disappear
    0.06
     hailed
    0.06
     techniques
    0.06
    _minute
    0.06
     brokers
    0.06
    orgia
    0.06
    Act Density 0.876%

    No Known Activations