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

    Neuronpedia

    INDEX
    Explanations

    Group theory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fillable
    -0.07
    안마
    -0.07
     й
    -0.07
     bottoms
    -0.06
    @Module
    -0.06
     juvenile
    -0.06
    、大
    -0.06
     xa
    -0.06
    Основ
    -0.06
    _ATTACH
    -0.06
    POSITIVE LOGITS
     commented
    0.06
     spectator
    0.06
    WN
    0.06
    urrencies
    0.06
    sim
    0.06
    {n
    0.06
    agrams
    0.06
    _trace
    0.06
     Facts
    0.05
     textbooks
    0.05
    Act Density 0.014%

    No Known Activations