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

    Neuronpedia

    INDEX
    Explanations

    technical terms and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bravely
    0.44
     rápidamente
    0.37
     frumo
    0.36
     happily
    0.36
     definizione
    0.36
    简介
    0.35
     энерго
    0.35
     tirelessly
    0.35
     Scrooge
    0.35
    的话
    0.34
    POSITIVE LOGITS
     depends
    0.45
     varies
    0.44
    是多少
    0.41
    以及
    0.40
     compared
    0.39
    被
    0.37
     transaction
    0.37
     is
    0.36
     differed
    0.36
    depends
    0.36
    Act Density 0.266%

    No Known Activations