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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing agreement or positive sentiment

    oai_token-act-pair · gemini-2.0-flash

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rospy
    -0.66
     ويكيميديا
    -0.65
    Дереккөздер
    -0.57
    retweeted
    -0.57
    gdala
    -0.56
    tahui
    -0.54
    //});
    -0.54
    ftagPool
    -0.53
    transQ
    -0.52
     magasiner
    -0.52
    POSITIVE LOGITS
    rildi
    0.55
    utives
    0.55
    TestTools
    0.52
     <<<<<<<<<<<<<<
    0.50
     }{@
    0.50
    FontOfSize
    0.47
    Démographie
    0.46
    :"-"`
    0.46
     ilu
    0.44
    itattu
    0.43
    Act Density 0.626%

    No Known Activations