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

    Neuronpedia

    INDEX
    Explanations

    graphics drawing commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Management
    0.41
     प्रबंधन
    0.41
    챈
    0.41
     Management
    0.41
     management
    0.39
     South
    0.38
     SQ
    0.38
     SOUTH
    0.37
     MANAGEMENT
    0.36
    ட்சிய
    0.35
    POSITIVE LOGITS
    dashed
    0.75
    dense
    0.65
     densely
    0.65
    rounded
    0.59
     dense
    0.57
     dashed
    0.57
    dens
    0.57
     rounded
    0.54
    dotted
    0.54
     ultra
    0.53
    Act Density 0.004%

    No Known Activations