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

    Neuronpedia

    INDEX
    Explanations

    sentence or paragraph descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Zad
    0.51
     svaki
    0.50
    helps
    0.50
     działa
    0.49
     Всем
    0.48
    කු
    0.48
    າ
    0.48
    बीआई
    0.47
    agnar
    0.47
     desgaste
    0.47
    POSITIVE LOGITS
    );
    0.44
    :
    0.43
     attrib
    0.43
     analyst
    0.42
    ISE
    0.42
     informed
    0.41
     requested
    0.40
    )
    0.40
    頃
    0.40
     pann
    0.39
    Act Density 0.001%

    No Known Activations