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

    Neuronpedia

    INDEX
    Explanations

    table column

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    graphics
    0.74
    Graphics
    0.72
     साध
    0.71
    স্থিত
    0.69
     Graphics
    0.67
    Alpes
    0.67
     रण
    0.66
    ві
    0.66
     czyn
    0.65
    minecraft
    0.64
    POSITIVE LOGITS
     column
    3.24
     columns
    3.20
    column
    2.91
    Column
    2.84
    columns
    2.82
     Column
    2.81
     Columns
    2.80
     columnas
    2.76
    Columns
    2.71
     columna
    2.62
    Act Density 0.516%

    No Known Activations