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

    Neuronpedia

    INDEX
    Explanations

    pronunciation guides and prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prototyping
    0.42
     scalable
    0.38
     FPGA
    0.37
     optimized
    0.37
     bidirectional
    0.36
     proactively
    0.35
     iteratively
    0.35
     Funktions
    0.35
     Kontext
    0.35
     hyped
    0.34
    POSITIVE LOGITS
     trifling
    0.39
     disagreeable
    0.34
     scorn
    0.34
     healthful
    0.32
     faculties
    0.32
     indignation
    0.31
     melancholy
    0.31
     alkalies
    0.31
     tumult
    0.31
     slumber
    0.31
    Act Density 0.013%

    No Known Activations