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

    Neuronpedia

    INDEX
    Explanations

    ist

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Analysis
    -0.07
    平板
    -0.07
    突破
    -0.07
     hope
    -0.07
    allocate
    -0.06
    有利
    -0.06
    绂
    -0.06
    ormap
    -0.06
    atism
    -0.06
    '^
    -0.06
    POSITIVE LOGITS
     dolphin
    0.07
    (seq
    0.07
    (from
    0.07
     defending
    0.07
    最初的
    0.07
     sometimes
    0.07
     wur
    0.07
    RIORITY
    0.06
    .deleted
    0.06
    blocking
    0.06
    Act Density 0.001%

    No Known Activations