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

    Neuronpedia

    INDEX
    Explanations

    mobile apps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gloves
    -0.07
    _SH
    -0.07
     layui
    -0.07
    ibrary
    -0.06
     бол
    -0.06
    छ
    -0.06
    렵
    -0.06
     Sand
    -0.06
    价格
    -0.06
    Fixture
    -0.06
    POSITIVE LOGITS
    YG
    0.07
    *↵
    0.07
    Joe
    0.07
     grabbing
    0.06
    ator
    0.06
     Lun
    0.06
    ład
    0.06
    >To
    0.06
     OMG
    0.06
    voy
    0.06
    Act Density 0.006%

    No Known Activations