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

    Neuronpedia

    INDEX
    Explanations

    bullet points

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arrera
    -0.07
    ospital
    -0.06
     nutritional
    -0.06
     collisions
    -0.06
     gross
    -0.06
    zego
    -0.06
    iciel
    -0.06
    /target
    -0.06
     ores
    -0.06
     deutschen
    -0.06
    POSITIVE LOGITS
    ді
    0.07
     المك
    0.06
    sects
    0.06
    0.06
    чается
    0.06
    _usb
    0.06
    objects
    0.06
    rtle
    0.06
    eceği
    0.06
     ErrorMessage
    0.06
    Act Density 0.038%

    No Known Activations