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

    Neuronpedia

    INDEX
    Explanations

    would apply to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kiş
    0.50
    我想
    0.49
     jumbo
    0.48
     liquido
    0.48
    但我
    0.47
     gigante
    0.47
     počas
    0.47
     pagina
    0.46
     workbook
    0.46
     umur
    0.46
    POSITIVE LOGITS
     sacks
    0.56
     arrangements
    0.54
     meats
    0.49
    orney
    0.49
     modalities
    0.49
     deposits
    0.47
    DataXYZ
    0.47
     resolves
    0.47
     initiates
    0.46
    ated
    0.46
    Act Density 0.000%

    No Known Activations