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

    Neuronpedia

    INDEX
    Explanations

    receiving actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     طراحی
    0.31
    を作成
    0.30
     fördern
    0.30
     برای
    0.29
     sør
    0.29
    廣告
    0.28
     உருவாக்கு
    0.27
     činjen
    0.26
    ensure
    0.26
    ál
    0.26
    POSITIVE LOGITS
     receive
    0.46
     receives
    0.40
     recibe
    0.40
     become
    0.38
     consented
    0.38
     suffers
    0.37
     received
    0.36
     recibir
    0.36
     receber
    0.36
     complained
    0.35
    Act Density 0.177%

    No Known Activations