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

    Neuronpedia

    INDEX
    Explanations

    URLs and references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ao
    -0.06
    .pass
    -0.06
     tabla
    -0.06
    uct
    -0.06
     AO
    -0.06
     ти
    -0.06
    patrick
    -0.06
     리
    -0.06
     zero
    -0.06
    Nuevo
    -0.06
    POSITIVE LOGITS
    lvl
    0.07
    PPER
    0.06
     Sy
    0.06
    NER
    0.06
    Bounds
    0.06
    assist
    0.06
    Apr
    0.06
    imiter
    0.06
    flatMap
    0.06
     Islamist
    0.06
    Act Density 0.001%

    No Known Activations