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

    Neuronpedia

    INDEX
    Explanations

    sudo apt commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अवगत
    0.78
     বৎসর
    0.76
     તથા
    0.74
     appreciably
    0.73
    ıdır
    0.72
     характеризу
    0.71
     abstracted
    0.71
    oidal
    0.70
     variabel
    0.70
     contextual
    0.70
    POSITIVE LOGITS
     horrifying
    1.41
     heartbreaking
    1.37
     horrified
    1.37
     TikTok
    1.33
     hilarious
    1.31
     shocking
    1.27
     terrifying
    1.26
    TikTok
    1.26
     YouTuber
    1.22
     horror
    1.20
    Act Density 0.059%

    No Known Activations