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

    Neuronpedia

    INDEX
    Explanations

    printing to stdout and stderr

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    瀾
    0.40
     SR
    0.39
    awan
    0.38
     Sen
    0.36
    amis
    0.36
    aient
    0.36
     裏
    0.36
    ರೆ
    0.35
    amise
    0.35
    unik
    0.35
    POSITIVE LOGITS
    ("\
    0.45
     {}\
    0.42
    ">\
    0.42
    Stdout
    0.40
    Sys
    0.39
    KERN
    0.39
    Certainly
    0.39
    .*\
    0.39
    髯
    0.39
    "\
    0.39
    Act Density 0.017%

    No Known Activations