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

    Neuronpedia

    INDEX
    Explanations

    advantage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _m
    -0.07
    /ec
    -0.07
     esports
    -0.07
     Ul
    -0.06
    -be
    -0.06
    _d
    -0.06
    .uc
    -0.06
     dic
    -0.06
    _c
    -0.06
    Us
    -0.06
    POSITIVE LOGITS
    ریف
    0.07
    AMY
    0.07
     Strip
    0.06
    amo
    0.06
    ubbo
    0.06
     resizable
    0.06
    amy
    0.06
    يف
    0.06
    _Entity
    0.06
     Конститу
    0.06
    Act Density 0.001%

    No Known Activations