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

    Neuronpedia

    INDEX
    Explanations

    function calls and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anyway
    0.89
     anyways
    0.87
    })(
    0.78
    ですので
    0.74
     Bei
    0.73
    ளமான
    0.73
     重要
    0.71
    ~(
    0.71
     \[
    0.71
     $(
    0.70
    POSITIVE LOGITS
    ()
    3.41
    ();
    2.85
    (),
    2.77
    ().
    2.74
    ())
    2.73
    ():
    2.72
     ()
    2.68
    (){
    2.55
    ());
    2.45
    ()))
    2.41
    Act Density 0.166%

    No Known Activations