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

    Neuronpedia

    INDEX
    Explanations

    bench, insured, people, unity, edit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _TRNS
    -0.08
     -*-č\n
    -0.08
    ¶Į
    -0.07
    \Dependency
    -0.07
    ·¸
    -0.07
    gii
    -0.07
    mobx
    -0.07
    noteq
    -0.07
    lient
    -0.07
    onymous
    -0.07
    POSITIVE LOGITS
    raquo
    0.08
    .Selenium
    0.08
    ARGS
    0.08
     âĨIJ
    0.07
     and
    0.07
     tpl
    0.07
     numerator
    0.06
    erville
    0.06
     itself
    0.06
    ãģ¾ãģļ
    0.06
    Act Density 2.392%

    No Known Activations