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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oxy
    -0.07
    част
    -0.07
     GF
    -0.07
     dài
    -0.07
     elim
    -0.07
    夕
    -0.06
    側
    -0.06
     Diane
    -0.06
    \Seeder
    -0.06
    ƒ
    -0.06
    POSITIVE LOGITS
    ="<<
    0.07
     ka
    0.06
    etsk
    0.06
    rop
    0.06
    -<?
    0.06
    anean
    0.06
    정부
    0.06
    랜
    0.06
     named
    0.05
    (candidate
    0.05
    Act Density 0.061%

    No Known Activations