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

    Neuronpedia

    INDEX
    Explanations

    first

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    伝
    -0.06
    フト
    -0.06
    ยาย
    -0.06
     accommodate
    -0.06
     хто
    -0.06
    _OLD
    -0.06
     подав
    -0.06
    ालय
    -0.06
    Todos
    -0.06
    Debugger
    -0.06
    POSITIVE LOGITS
    .rd
    0.07
     sele
    0.06
    .arch
    0.06
    avior
    0.06
     Wolfe
    0.06
    ิศาสตร
    0.06
    .Window
    0.06
     Shoulder
    0.06
     Druid
    0.06
     Frost
    0.06
    Act Density 0.010%

    No Known Activations