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

    Neuronpedia

    INDEX
    Explanations

    function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aquello
    0.49
    кологи
    0.37
    CRIPTOR
    0.37
    皋
    0.37
    覤
    0.37
    ستون
    0.37
     sämt
    0.36
    द्य
    0.36
    azón
    0.35
    солю
    0.34
    POSITIVE LOGITS
    (
    0.70
    _(
    0.69
    ($
    0.68
    (_
    0.67
    ()
    0.63
    (&
    0.62
     $(
    0.59
    (){
    0.59
    (),
    0.57
    __(
    0.57
    Act Density 0.085%

    No Known Activations