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

    Neuronpedia

    INDEX
    Explanations

    sleeve

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     Bloss
    -0.07
    悆
    -0.06
     nær
    -0.06
     curses
    -0.06
    🍈
    -0.06
    łoży
    -0.06
    onders
    -0.06
    気軽
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     sleeves
    0.08
    带
    0.07
     REPLACE
    0.07
     persuasion
    0.07
     sleeve
    0.07
     sửa
    0.07
     JVM
    0.07
    ";
    0.07
    set
    0.07
    避免
    0.07
    Act Density 0.002%

    No Known Activations