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

    Neuronpedia

    INDEX
    Explanations

    authority

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RESULTS
    -0.06
     recognizable
    -0.06
     gerade
    -0.06
     renew
    -0.06
     визнач
    -0.06
     fireworks
    -0.06
     SIZE
    -0.06
     若要
    -0.06
    erequisites
    -0.06
     Grade
    -0.06
    POSITIVE LOGITS
     authority
    0.21
    authority
    0.14
     Authority
    0.13
    Authority
    0.11
     authoritative
    0.08
    apyrus
    0.07
     portrayal
    0.07
    まと
    0.07
    ving
    0.07
     اسپ
    0.07
    Act Density 0.005%

    No Known Activations