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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     rit
    -0.07
     gains
    -0.07
     Francisco
    -0.07
    ĝ
    -0.06
    ทำ
    -0.06
     agreed
    -0.06
    uffman
    -0.06
    ci
    -0.06
    ");↵↵↵
    -0.06
    (mu
    -0.06
    POSITIVE LOGITS
    ನ
    0.07
    ordered
    0.07
    กรรม
    0.07
     adultes
    0.07
     getView
    0.07
     למרות
    0.07
    佸
    0.06
    אנגלית
    0.06
    ebileceği
    0.06
    垏
    0.06
    Act Density 0.005%

    No Known Activations