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

    Neuronpedia

    INDEX
    Explanations

    main() function entry point

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     রাস
    0.37
    binghamton
    0.36
     likewise
    0.34
    ）；
    0.34
    attiyam
    0.33
    ';...
    0.33
    阳
    0.33
    ]);}
    0.33
    长大
    0.33
    ;
    0.32
    POSITIVE LOGITS
    ()
    1.10
    (){
    1.05
     ()
    1.02
     (){
    0.88
    ():
    0.82
     ():
    0.71
    ()){
    0.69
    ()"
    0.67
    ()\
    0.62
    ().
    0.61
    Act Density 0.012%

    No Known Activations