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

    Neuronpedia

    INDEX
    Explanations

    Code/special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    marca
    -0.08
    жа
    -0.07
     classrooms
    -0.07
    ής
    -0.07
    ульта
    -0.07
     rizik
    -0.06
    )dealloc
    -0.06
    ukes
    -0.06
     накоп
    -0.06
    běh
    -0.06
    POSITIVE LOGITS
    기준
    0.07
    _message
    0.06
    敵
    0.06
     places
    0.06
     Year
    0.06
    -transparent
    0.06
    ив
    0.06
    .swift
    0.06
     Cowboy
    0.06
    ogenic
    0.06
    Act Density 0.000%

    No Known Activations