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

    Neuronpedia

    INDEX
    Explanations

    invasive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     millionaire
    -0.07
     Winners
    -0.07
    Arch
    -0.07
    �
    -0.06
    álie
    -0.06
    .protocol
    -0.06
    renc
    -0.06
     AHL
    -0.06
     desn
    -0.06
    efeller
    -0.06
    POSITIVE LOGITS
     invasive
    0.28
    vasive
    0.20
     HOLDERS
    0.07
    .Select
    0.07
    ondrous
    0.07
    勢
    0.07
     بوابة
    0.07
     kurum
    0.06
     refute
    0.06
     seaw
    0.06
    Act Density 0.002%

    No Known Activations