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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BlockSize
    -0.07
     N
    -0.07
     又
    -0.06
     mơ
    -0.06
    Anthony
    -0.06
    นาด
    -0.06
     "@"
    -0.06
    Superview
    -0.06
     renting
    -0.06
    science
    -0.06
    POSITIVE LOGITS
    progress
    0.07
     monstr
    0.06
    BACKGROUND
    0.06
     ipv
    0.06
     Improvement
    0.06
     xuyên
    0.06
    '](
    0.05
    ，然后
    0.05
    .SqlClient
    0.05
    aea
    0.05
    Act Density 0.005%

    No Known Activations