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

    Neuronpedia

    INDEX
    Explanations

    mathematical sequences and sets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     двумя
    -0.93
     大学
    -0.79
     ambos
    -0.78
    Ꭻ
    -0.74
    Four
    -0.73
     skóry
    -0.71
    QualifiedName
    -0.69
    =?";
    -0.69
    velmente
    -0.68
     talked
    -0.68
    POSITIVE LOGITS
     $\{
    2.30
     \{
    1.94
     $\{\
    1.90
     {
    1.78
    $\{
    1.77
    \{
    1.68
     $\{$
    1.41
     {
    1.36
    ,{
    1.33
     \{\
    1.30
    Act Density 0.053%

    No Known Activations