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

    Neuronpedia

    INDEX
    Explanations

    expressing gratitude and intensity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     podob
    0.38
     subconsciously
    0.38
     jika
    0.37
     Gradually
    0.37
     gradually
    0.36
     logical
    0.36
     şöyle
    0.36
     predictably
    0.36
     logically
    0.36
     videre
    0.36
    POSITIVE LOGITS
     столь
    0.81
     এতো
    0.61
     এত
    0.59
    这么
    0.58
     इतनी
    0.54
    这么多
    0.53
     इतने
    0.52
    এত
    0.51
     wonderful
    0.49
    這麼
    0.49
    Act Density 0.068%

    No Known Activations