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

    Neuronpedia

    INDEX
    Explanations

    fulfill

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tur
    -0.08
    Shade
    -0.08
     Rhine
    -0.08
     Greenland
    -0.08
     Dark
    -0.07
    Dark
    -0.07
     Frederick
    -0.07
    톤
    -0.07
    TMP
    -0.07
    dienst
    -0.07
    POSITIVE LOGITS
     obligations
    0.11
    使命
    0.10
     निभ
    0.09
     obligation
    0.09
     erfüllen
    0.09
     требований
    0.08
     обязанности
    0.08
     requirements
    0.08
     obligated
    0.08
     требования
    0.08
    Act Density 0.019%

    No Known Activations