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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ()=>{
    2.15
    ',()=>{
    1.87
    ',{
    1.86
     ()=>
    1.86
       
    1.79
    ={()=>
    1.79
    ",{
    1.76
    =""/>
    1.72
    ',(
    1.69
    />}
    1.68
    POSITIVE LOGITS
    <unused105>
    0.84
     /**
    0.75
     \|
    0.73
    <unused1981>
    0.71
     zudem
    0.70
     überhaupt
    0.66
     Zudem
    0.65
     samme
    0.64
     sekaligus
    0.64
     pār
    0.64
    Act Density 0.027%

    No Known Activations