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

    Neuronpedia

    INDEX
    Explanations

    facade

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hh
    -0.06
    ذار
    -0.06
     나는
    -0.06
    lahoma
    -0.06
    들의
    -0.06
    sss
    -0.06
     部
    -0.06
     Strait
    -0.06
     Girl
    -0.05
     هذا
    -0.05
    POSITIVE LOGITS
    .struct
    0.07
     auditing
    0.07
     advertisers
    0.07
     flexibility
    0.07
     advertising
    0.07
     ved
    0.06
    Uniform
    0.06
    희
    0.06
    atatype
    0.06
    (eval
    0.06
    Act Density 0.011%

    No Known Activations