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

    Neuronpedia

    INDEX
    Explanations

    create our own meaning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     এবং
    0.46
     và
    0.44
     and
    0.44
     Banking
    0.42
     Imped
    0.42
     Automotive
    0.42
    dedicated
    0.42
     Veh
    0.41
    :
    0.41
     terhadap
    0.41
    POSITIVE LOGITS
     стрем
    0.54
     свадь
    0.47
     стреми
    0.46
    시
    0.42
    äden
    0.42
    ಏ
    0.42
    趋势
    0.41
    निव
    0.41
     경우
    0.40
     спа
    0.40
    Act Density 0.004%

    No Known Activations