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

    Neuronpedia

    INDEX
    Explanations

    javascript function calls and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )>=
    0.50
    乃至
    0.45
    )==
    0.41
    ўкі
    0.40
    )!=
    0.38
    oblot
    0.38
    چہ
    0.37
    軗
    0.37
    owią
    0.36
    )]^{
    0.36
    POSITIVE LOGITS
    (){
    0.93
     (){
    0.86
     ()
    0.86
    ()
    0.73
    (
    0.70
     (
    0.68
     (_)
    0.58
    ()){
    0.52
    ($
    0.52
    *(
    0.50
    Act Density 0.003%

    No Known Activations