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

    Neuronpedia

    INDEX
    Explanations

    are committed to action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    或
    0.52
     或
    0.50
     melanch
    0.49
     живота
    0.49
    手表
    0.47
    食物
    0.47
    皮肤
    0.47
    тив
    0.46
     解
    0.46
     ആയിരുന്നു
    0.46
    POSITIVE LOGITS
    ad
    0.80
    im
    0.71
    ag
    0.62
    no
    0.59
    en
    0.56
    on
    0.56
     इनोवेशन
    0.55
     financing
    0.53
     nonprofits
    0.53
    U
    0.53
    Act Density 0.119%

    No Known Activations