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

    Neuronpedia

    INDEX
    Explanations

    explaining production or outcome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rins
    0.54
    nya
    0.49
    z
    0.49
    is
    0.48
    idd
    0.47
    niejs
    0.47
    peng
    0.46
    itano
    0.46
    swear
    0.46
     HttpClient
    0.45
    POSITIVE LOGITS
     воспа
    0.52
     contrô
    0.52
    負荷
    0.51
     systém
    0.50
    遊び
    0.49
    ℙ
    0.49
     cellules
    0.48
    ξι
    0.48
    発
    0.48
    Databaze
    0.48
    Act Density 0.000%

    No Known Activations