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

    Neuronpedia

    INDEX
    Explanations

    function calls or definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     그리고
    0.83
    শিং
    0.81
     resisted
    0.78
     وض
    0.76
     ​​
    0.74
     $+
    0.73
    going
    0.73
     Sexton
    0.71
     σύμφωνα
    0.71
     оформления
    0.71
    POSITIVE LOGITS
    (){
    1.49
    (_,
    1.21
     ){
    1.18
    ){
    1.16
    ()){
    1.12
     (){
    1.10
     ()
    1.07
    (__
    1.06
    (_
    1.04
    ality
    1.04
    Act Density 0.001%

    No Known Activations