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

    Neuronpedia

    INDEX
    Explanations

    offers options, ranging, categorized

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,?
    0.42
    ،
    0.42
    ,
    0.38
    ,</
    0.37
    ，
    0.37
    \%,
    0.36
    ,​
    0.36
    .$,
    0.35
     হউক
    0.35
    =?,
    0.34
    POSITIVE LOGITS
    that
    0.61
    along
    0.55
    etc
    0.54
     ஆகிய
    0.54
     reminding
    0.52
     которые
    0.51
    그리고
    0.49
     ஆகியவற்ற
    0.49
    と共に
    0.49
     которая
    0.49
    Act Density 0.138%

    No Known Activations