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

    Neuronpedia

    INDEX
    Explanations

    recurrence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ат
    0.56
    iszt
    0.55
    ώ
    0.55
    一個
    0.54
    يح
    0.54
    ين
    0.53
     उपभो
    0.52
    ہم
    0.52
     aceptación
    0.51
     Приступљено
    0.51
    POSITIVE LOGITS
    vertical
    0.53
     horizontal
    0.51
    LL
    0.50
     Horizontal
    0.50
    د
    0.49
    Horizontal
    0.49
     lateral
    0.49
     Lateral
    0.49
    ->
    0.48
     Anne
    0.48
    Act Density 0.000%

    No Known Activations