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

    Neuronpedia

    INDEX
    Explanations

    key

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     const
    -0.08
    ]):
    -0.08
    _in
    -0.07
    יפה
    -0.07
    Sum
    -0.07
    ");//
    -0.07
    ]int
    -0.07
    俄军
    -0.07
     exponential
    -0.07
     vol
    -0.07
    POSITIVE LOGITS
     następ
    0.07
     rooft
    0.07
     Minority
    0.07
    亥
    0.07
    邙
    0.07
    gend
    0.07
     bır
    0.07
    .ResponseWriter
    0.06
    ﹼ
    0.06
    웨
    0.06
    Act Density 0.004%

    No Known Activations