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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    甜
    -0.07
     가져
    -0.06
    .setToolTipText
    -0.06
    $select
    -0.06
    �
    -0.06
    lantı
    -0.06
    ۱۹۴
    -0.06
    _trap
    -0.06
    externalActionCode
    -0.06
    umba
    -0.06
    POSITIVE LOGITS
     steel
    0.07
    创新
    0.07
     Dyn
    0.07
    东省
    0.06
    plete
    0.06
    gence
    0.06
    нить
    0.06
    WOOD
    0.06
    Breaking
    0.06
     منه
    0.06
    Act Density 0.070%

    No Known Activations