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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Current
    -0.07
     MANAGEMENT
    -0.06
     Memories
    -0.06
    "M
    -0.06
     Apartment
    -0.06
    -compatible
    -0.06
     smokers
    -0.06
     Management
    -0.06
     forefront
    -0.06
    _reporting
    -0.06
    POSITIVE LOGITS
     см
    0.07
    lassen
    0.07
     ド
    0.07
    ΙΚ
    0.07
    تغ
    0.07
     insanın
    0.06
     tweak
    0.06
     Aspen
    0.06
     Volkswagen
    0.06
    řila
    0.06
    Act Density 0.011%

    No Known Activations