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

    Neuronpedia

    INDEX
    Explanations

    positive affirmations and greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    疋
    0.33
    тьяна
    0.32
     timestep
    0.32
     увагу
    0.32
    呵呵
    0.32
    adakan
    0.32
    があるので
    0.32
     furl
    0.31
    なかったので
    0.31
     защото
    0.31
    POSITIVE LOGITS
    !
    0.74
    ！
    0.66
    !;
    0.59
    ！（
    0.59
    !!
    0.57
    !"
    0.56
    !”
    0.55
    !“
    0.55
    !</
    0.53
    !)
    0.52
    Act Density 0.008%

    No Known Activations