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

    Neuronpedia

    INDEX
    Explanations

    agree

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ेरी
    -0.08
     succeed
    -0.08
    Louis
    -0.07
    ित्व
    -0.07
    Sue
    -0.07
     мысл
    -0.07
     परी
    -0.07
     приходится
    -0.07
     ישראל
    -0.07
     succeeds
    -0.07
    POSITIVE LOGITS
     agreements
    0.11
     acuerdos
    0.11
    协议
    0.11
    双方
    0.11
     Agreements
    0.11
     acuer
    0.11
     agreement
    0.10
     بشأن
    0.10
     מראש
    0.10
     договор
    0.10
    Act Density 0.046%

    No Known Activations