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

    Neuronpedia

    INDEX
    Explanations

    file operations and commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Powell
    0.39
    oying
    0.38
    ):\
    0.37
    &&&&
    0.36
     {-
    0.36
    ूत
    0.36
    urten
    0.36
    rocyte
    0.36
     AssetImage
    0.36
     ومت
    0.36
    POSITIVE LOGITS
     teslim
    0.42
     chopper
    0.40
     copos
    0.39
     continuare
    0.38
     přest
    0.38
     fowl
    0.37
     Lieferung
    0.37
     ditth
    0.37
     RULES
    0.36
    0.36
    Act Density 0.000%

    No Known Activations