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

    Neuronpedia

    INDEX
    Explanations

    coding questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Collection
    -0.07
     mixed
    -0.06
    iyel
    -0.06
    تمبر
    -0.06
    IH
    -0.06
     هر
    -0.06
    (detail
    -0.06
     NAND
    -0.06
     pursue
    -0.06
    )?.
    -0.06
    POSITIVE LOGITS
    rc
    0.06
    _proxy
    0.06
    urf
    0.06
     weld
    0.06
    관리자
    0.06
    -builder
    0.06
    otime
    0.06
    ADE
    0.06
     accumulator
    0.06
    -&
    0.06
    Act Density 0.076%

    No Known Activations