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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ≿
    -0.08
    ♌
    -0.07
    _OPCODE
    -0.07
    垂直
    -0.07
    LoadIdentity
    -0.07
    盈
    -0.07
    Ј
    -0.06
     January
    -0.06
    Italy
    -0.06
    腾飞
    -0.06
    POSITIVE LOGITS
    efs
    0.08
    ensored
    0.07
     harassed
    0.07
     explores
    0.07
    aviours
    0.07
    Benchmark
    0.07
    (bounds
    0.07
     Toilet
    0.07
    locales
    0.06
     bark
    0.06
    Act Density 0.057%

    No Known Activations