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

    Neuronpedia

    INDEX
    Explanations

    harmful exposure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -place
    -0.07
     하는
    -0.06
    _ALIGNMENT
    -0.06
    Location
    -0.06
    _Unit
    -0.06
    .DependencyInjection
    -0.06
    ('/
    -0.06
     IDEOGRAPH
    -0.06
     irresistible
    -0.06
    luent
    -0.06
    POSITIVE LOGITS
    Debe
    0.06
     tòa
    0.06
     Michel
    0.06
     мел
    0.06
    him
    0.06
    155
    0.06
     신
    0.06
     relied
    0.06
    liable
    0.06
     فراو
    0.06
    Act Density 0.023%

    No Known Activations